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

    Neuronpedia

    INDEX
    Explanations

    sunglasses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пок
    -0.06
    Our
    -0.06
    Emb
    -0.06
    ModelError
    -0.06
     Teen
    -0.06
    (writer
    -0.06
     Our
    -0.06
     Cave
    -0.06
    apeutic
    -0.06
    .databind
    -0.06
    POSITIVE LOGITS
     glasses
    0.08
     Glasses
    0.08
     cout
    0.07
    lasses
    0.07
     gobierno
    0.07
    HW
    0.07
     pagamento
    0.07
     وجه
    0.07
     tık
    0.06
     glyc
    0.06
    Act Density 0.007%

    No Known Activations