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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oks
    -0.06
    оном
    -0.06
    روج
    -0.06
    .,↵
    -0.06
    doctor
    -0.06
     Hakk
    -0.06
     порт
    -0.06
    ermo
    -0.06
     resident
    -0.06
     '''
↵
    -0.06
    POSITIVE LOGITS
     φ
    0.07
     bloodstream
    0.07
    .responseText
    0.07
    /core
    0.06
    (sock
    0.06
    .mozilla
    0.06
    _var
    0.06
     []*
    0.06
    mouseout
    0.06
     كر
    0.06
    Act Density 0.002%

    No Known Activations