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

    Neuronpedia

    INDEX
    Explanations

    philanthropic endeavors and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.09
    on
    1.06
    ä
    1.01
    as
    0.97
    ro
    0.97
    2
    0.91
    r
    0.88
    g
    0.86
    os
    0.85
    c
    0.80
    POSITIVE LOGITS
    ק
    0.89
     philanthropic
    0.84
    娯
    0.84
     artístico
    0.80
     przyję
    0.79
     arrêté
    0.79
     peruse
    0.77
     impose
    0.77
     apoyo
    0.76
    ও
    0.75
    Act Density 0.004%

    No Known Activations