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

    Neuronpedia

    INDEX
    Explanations

    programming language structs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.23
    h
    1.11
    x
    0.99
    am
    0.96
    on
    0.95
    w
    0.89
    f
    0.88
    k
    0.88
    et
    0.88
    פ
    0.87
    POSITIVE LOGITS
    ین
    1.07
    لي
    0.87
    speople
    0.85
    یک
    0.82
     is
    0.82
    smanship
    0.81
     kehadiran
    0.79
     keber
    0.77
     shelters
    0.77
    shells
    0.76
    Act Density 0.002%

    No Known Activations