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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suing
    -0.07
    емся
    -0.07
    ceeded
    -0.07
    >Action
    -0.07
    LETED
    -0.07
    _aa
    -0.07
     związku
    -0.07
    .spawn
    -0.06
    юсь
    -0.06
    喁
    -0.06
    POSITIVE LOGITS
    .Mod
    0.08
    pe
    0.08
    凄
    0.08
     Lis
    0.07
     Kro
    0.07
    /*.
    0.07
     iPhone
    0.07
    迭
    0.07
    cke
    0.07
     Lac
    0.07
    Act Density 0.042%

    No Known Activations