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

    Neuronpedia

    INDEX
    Explanations

    Hexadecimal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     historian
    -0.07
    Jose
    -0.06
     Davidson
    -0.06
    аліст
    -0.06
     Bul
    -0.06
    Pol
    -0.06
    Expression
    -0.06
    .Device
    -0.06
     discourse
    -0.06
     úřad
    -0.06
    POSITIVE LOGITS
     též
    0.08
    ΟΣ
    0.07
    ยวข
    0.06
     }])↵
    0.06
    usses
    0.06
    ційних
    0.06
     scoop
    0.06
    иг
    0.06
    आई
    0.06
    ']")↵
    0.06
    Act Density 0.013%

    No Known Activations