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

    Neuronpedia

    INDEX
    Explanations

    open spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     software
    -0.09
    ینو
    -0.09
     softwares
    -0.08
     stabilization
    -0.08
     সফ
    -0.08
     Bib
    -0.08
    _PATCH
    -0.07
     şey
    -0.07
    软件
    -0.07
     ڇا
    -0.07
    POSITIVE LOGITS
    Transparency
    0.10
    Visibility
    0.10
    透明
    0.10
    无遮
    0.09
     transparency
    0.09
     transparencia
    0.09
     perme
    0.09
     visibilité
    0.09
    Monitor
    0.09
     openness
    0.09
    Act Density 0.058%

    No Known Activations