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

    Neuronpedia

    INDEX
    Explanations

    Instructions and procedures

    np_max-act · gemini-2.0-flash

    The neuron detects floating-point numbers (numeric constants containing a decimal point) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    these
    -0.07
    blr
    -0.07
    algo
    -0.07
     timespec
    -0.06
    Expiration
    -0.06
     �
    -0.06
    Message
    -0.06
     พร
    -0.06
     protections
    -0.06
    stores
    -0.06
    POSITIVE LOGITS
     mainland
    0.06
     Hate
    0.06
     Yield
    0.06
     zám
    0.06
    .exists
    0.06
    Но
    0.06
     Fact
    0.06
     RAD
    0.06
     FACT
    0.06
    ITOR
    0.06
    Act Density 0.076%

    No Known Activations