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

    Neuronpedia

    INDEX
    Explanations

    Programming code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ९
    -0.07
    乌
    -0.07
    LOAT
    -0.06
     grad
    -0.06
    ₃
    -0.06
     kk
    -0.06
     jihadists
    -0.06
    imator
    -0.06
     Sacred
    -0.06
    .obj
    -0.06
    POSITIVE LOGITS
     compart
    0.07
    =random
    0.07
    نب
    0.06
     Tibet
    0.06
     рок
    0.06
    бер
    0.06
     blas
    0.06
     Loaded
    0.06
    _SERVICE
    0.06
     orders
    0.06
    Act Density 0.005%

    No Known Activations