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

    Neuronpedia

    INDEX
    Explanations

    Accidents, unintended consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gemeint
    -0.61
     venons
    -0.61
     unintentionally
    -0.60
     llorando
    -0.60
     automatiques
    -0.59
     متعلقه
    -0.59
     unwittingly
    -0.58
     inadvertently
    -0.57
     unconsciously
    -0.57
    RetentionPolicy
    -0.56
    POSITIVE LOGITS
    RTLR
    0.64
     Roskov
    0.58
    ulon
    0.50
    AccessorTable
    0.48
     @"/
    0.48
    mstyle
    0.47
     torr
    0.47
    encodeWith
    0.47
    帖最后由
    0.47
    GetEnumerator
    0.46
    Act Density 0.018%

    No Known Activations