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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menu
    -0.07
    /python
    -0.06
    _tables
    -0.06
     academics
    -0.06
     furniture
    -0.06
     praised
    -0.06
    spaces
    -0.06
    /default
    -0.06
    ib
    -0.06
    _();↵
    -0.06
    POSITIVE LOGITS
    _SSL
    0.07
    사회
    0.07
    ğen
    0.07
    .navigationBar
    0.07
    .tintColor
    0.07
     цього
    0.07
     tươi
    0.07
    .DecimalField
    0.07
    ทำให
    0.07
    #----------------------------------------------------------------
    0.07
    Act Density 0.144%

    No Known Activations