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

    Neuronpedia

    INDEX
    Explanations

    Change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phones
    -0.07
     cooperate
    -0.06
    _normal
    -0.06
     يد
    -0.06
     items
    -0.06
     Early
    -0.06
     guitar
    -0.06
     PLAYER
    -0.06
     phone
    -0.06
     refugees
    -0.06
    POSITIVE LOGITS
     내려
    0.06
     yeri
    0.06
    .i
    0.06
    lüğ
    0.06
     فرمود
    0.06
     Киє
    0.06
    isEqualTo
    0.06
     Králové
    0.06
    ↵    ↵
    0.06
    oracle
    0.06
    Act Density 0.183%

    No Known Activations