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

    Neuronpedia

    INDEX
    Explanations

    Yosemite National Park

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.80
    d
    0.77
    l
    0.70
    r
    0.66
    thest
    0.63
    ER
    0.61
    k
    0.60
    g
    0.59
    h
    0.59
    ORF
    0.58
    POSITIVE LOGITS
     be
    0.85
     mês
    0.69
    ří
    0.68
     diario
    0.67
    ní
    0.66
     maanden
    0.66
     اليوم
    0.64
     což
    0.62
     etwas
    0.61
     svou
    0.61
    Act Density 0.005%

    No Known Activations