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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literals (integer or decimal) appearing in list or tuple contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .dart
    -0.08
    ////↵
    -0.07
    ]=[
    -0.06
    yster
    -0.06
    .jump
    -0.06
     Grocery
    -0.06
     šť
    -0.06
     Grandma
    -0.06
     некотор
    -0.06
    肯
    -0.06
    POSITIVE LOGITS
    /goto
    0.07
    .AppendLine
    0.07
    Allocate
    0.06
     participate
    0.06
     Citizenship
    0.06
     nationalists
    0.06
     trafficking
    0.06
    apsulation
    0.06
     phenomena
    0.06
    assessment
    0.06
    Act Density 0.041%

    No Known Activations