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

    Neuronpedia

    INDEX
    Explanations

    Talking about something specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bias
    -0.07
     이전
    -0.06
    .writeFileSync
    -0.06
    .Show
    -0.06
     RTVF
    -0.06
    .Annotations
    -0.06
    	State
    -0.06
     підт
    -0.06
    .dataset
    -0.06
     substring
    -0.06
    POSITIVE LOGITS
    SYS
    0.08
     Derrick
    0.07
     sino
    0.07
    �
    0.07
     during
    0.06
    ::::::::
    0.06
    ampiyon
    0.06
     criticized
    0.06
    creature
    0.06
    دری
    0.06
    Act Density 0.110%

    No Known Activations