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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.49
     daripada
    -0.49
    ly
    -0.47
    tanleria
    -0.47
    zydent
    -0.47
    Více
    -0.46
     pidana
    -0.46
     sää
    -0.43
    ↵↵
    -0.43
     nasional
    -0.42
    POSITIVE LOGITS
     contextLoads
    0.68
    tiller
    0.67
     permeability
    0.65
    ISupport
    0.64
     Permeability
    0.64
     فريبيس
    0.62
     nahilalakip
    0.61
     phag
    0.60
    saraba
    0.60
    enumii
    0.59
    Act Density 0.202%

    No Known Activations