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

    Neuronpedia

    INDEX
    Explanations

    Code file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שוב
    -0.07
     шаг
    -0.07
     miesię
    -0.07
     adım
    -0.07
    ,vector
    -0.07
     вещ
    -0.07
     hashing
    -0.07
     nông
    -0.06
    бро
    -0.06
    vro
    -0.06
    POSITIVE LOGITS
    座
    0.08
    [-
    0.08
     Parade
    0.07
     Batman
    0.07
     Mart
    0.07
    (profile
    0.07
    养老保险
    0.06
     Enemy
    0.06
     [{
    0.06
     apologized
    0.06
    Act Density 0.001%

    No Known Activations