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

    Neuronpedia

    INDEX
    Explanations

    packaging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cone
    -0.08
    outlined
    -0.07
     слыш
    -0.07
    ak
    -0.06
    .models
    -0.06
     Lid
    -0.06
     συμμε
    -0.06
    parated
    -0.06
    agle
    -0.06
     Sims
    -0.06
    POSITIVE LOGITS
     Swarm
    0.07
     Sebast
    0.06
    MethodImpl
    0.06
    .Tipo
    0.06
     meiden
    0.06
    欧
    0.06
     вас
    0.06
    usuario
    0.06
    _PRODUCT
    0.06
    歐
    0.06
    Act Density 0.020%

    No Known Activations