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

    Neuronpedia

    INDEX
    Explanations

    sad smileys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .apps
    -0.07
     occupied
    -0.07
     shortly
    -0.07
    _sign
    -0.07
     decryption
    -0.07
    .meta
    -0.06
    ┴
    -0.06
    sed
    -0.06
     slack
    -0.06
     boton
    -0.06
    POSITIVE LOGITS
     Chicken
    0.07
     Bu
    0.06
    Conta
    0.06
    人民共和国
    0.06
     Ürün
    0.06
    UN
    0.06
    Whether
    0.06
     Beaut
    0.06
    ipeg
    0.06
    LERİ
    0.06
    Act Density 0.004%

    No Known Activations