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

    Neuronpedia

    INDEX
    Explanations

    english

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hot
    -0.07
     dissatisfaction
    -0.07
     provinces
    -0.07
    -State
    -0.06
    _intersection
    -0.06
     Bans
    -0.06
     volupt
    -0.06
     králov
    -0.06
    -da
    -0.06
    Conditional
    -0.06
    POSITIVE LOGITS
    ník
    0.06
    Getting
    0.06
    新的
    0.06
    Feels
    0.06
    .BASE
    0.06
    -kind
    0.06
    .Peek
    0.06
     تمامی
    0.05
    ug
    0.05
    ुस
    0.05
    Act Density 0.053%

    No Known Activations