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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setVisibility
    -0.07
     SUS
    -0.07
     Bankası
    -0.07
    Kernel
    -0.06
    ml
    -0.06
     destac
    -0.06
    Free
    -0.06
    .activity
    -0.06
     autre
    -0.06
    _peak
    -0.06
    POSITIVE LOGITS
    Dao
    0.07
    ича
    0.07
     mö
    0.07
    forced
    0.07
    ":["
    0.06
     října
    0.06
    状況
    0.06
    dı
    0.06
    imiter
    0.06
    jeta
    0.06
    Act Density 0.083%

    No Known Activations