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

    Neuronpedia

    INDEX
    Explanations

    Name

    np_max-act · gemini-2.0-flash

    This neuron activates on placeholder identifiers (e.g., “NAME_1,” “NAME_2”) representing anonymized names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ']}'
    -0.07
     psychologists
    -0.07
     growth
    -0.07
    _hit
    -0.06
     foreign
    -0.06
    .Comp
    -0.06
     تح
    -0.06
     Deposit
    -0.06
     Trace
    -0.06
     VIII
    -0.06
    POSITIVE LOGITS
    áy
    0.07
    Toolbar
    0.07
    ognito
    0.07
     ミ
    0.06
    ầ
    0.06
     Miss
    0.06
    同时
    0.06
    燕
    0.06
    Recommended
    0.06
     downwards
    0.06
    Act Density 0.030%

    No Known Activations