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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     शांत
    -0.09
     tui
    -0.08
     শান্ত
    -0.08
     دفاع
    -0.08
     strengthening
    -0.08
    ٰ
    -0.08
    interrupt
    -0.08
     uphill
    -0.08
     unnoticed
    -0.07
    Foreground
    -0.07
    POSITIVE LOGITS
     Umgang
    0.08
     Stadium
    0.08
     Studio
    0.08
     Rename
    0.08
     Oficina
    0.08
     Maker
    0.08
    .Then
    0.08
     mung
    0.08
     casas
    0.07
     Затем
    0.07
    Act Density 0.047%

    No Known Activations