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

    Neuronpedia

    INDEX
    Explanations

    expectation and substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.59
    l
    0.56
    c
    0.52
    m
    0.52
    Dec
    0.49
    lh
    0.48
    u
    0.48
    emerg
    0.47
    ap
    0.47
    in
    0.47
    POSITIVE LOGITS
     Resultados
    0.48
     Ibid
    0.46
     بیټ
    0.43
     HONOR
    0.43
     पुराण
    0.43
    ]");
    0.41
     бет
    0.41
     نتیجه
    0.40
    ≣
    0.40
     सेल्फ
    0.40
    Act Density 0.002%

    No Known Activations