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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numeric tokens (both integers and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     reviewing
    -0.06
    ็ค
    -0.06
     especial
    -0.06
    -NLS
    -0.06
     audio
    -0.06
     cac
    -0.06
     oft
    -0.06
     público
    -0.06
    sec
    -0.06
    hf
    -0.06
    POSITIVE LOGITS
     GE
    0.07
    (info
    0.07
    ATTRIBUTE
    0.06
     WN
    0.06
     hydrogen
    0.06
    States
    0.06
    เกอร
    0.06
     Presented
    0.06
    _argument
    0.06
    .TO
    0.06
    Act Density 0.904%

    No Known Activations