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

    Neuronpedia

    INDEX
    Explanations

    harm or damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilden
    -0.07
    anners
    -0.07
    用品
    -0.07
    boru
    -0.07
     kisses
    -0.06
    -db
    -0.06
    С
    -0.06
     Beste
    -0.06
     Police
    -0.06
    _tweet
    -0.06
    POSITIVE LOGITS
    ateau
    0.08
     γ
    0.07
    endpoint
    0.06
    .vec
    0.06
    _instances
    0.06
    .gl
    0.06
     downt
    0.06
    .putInt
    0.06
    .opt
    0.06
    .addEdge
    0.06
    Act Density 0.039%

    No Known Activations