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

    Neuronpedia

    INDEX
    Explanations

    conversational language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عام
    -0.07
    _attached
    -0.06
     Et
    -0.06
     ElementType
    -0.06
    ety
    -0.06
    veis
    -0.06
     getIndex
    -0.05
    etary
    -0.05
     dél
    -0.05
     contain
    -0.05
    POSITIVE LOGITS
    ･･
    0.07
     [--
    0.07
    /small
    0.07
    'ı
    0.06
     arr
    0.06
    scene
    0.06
     hydro
    0.06
    -error
    0.06
     uninsured
    0.06
    bilder
    0.06
    Act Density 0.003%

    No Known Activations