Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    text related to coding examples for basic software functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect comparison operators and related conditional‐statement tokens (e.g. “==”, `if`, `elif`) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    belt
    -0.07
    ्पर
    -0.07
    .»
    -0.06
     onward
    -0.06
    逐
    -0.06
    820
    -0.06
     outskirts
    -0.06
     контр
    -0.06
    Ap
    -0.06
     copyrighted
    -0.05
    POSITIVE LOGITS
     milano
    0.07
     μπο
    0.07
    ediální
    0.07
     아
    0.07
     lowercase
    0.06
     وهو
    0.06
     plunged
    0.06
     слід
    0.06
    ไหน
    0.06
    Soap
    0.06
    Act Density 0.015%

    No Known Activations