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

    Neuronpedia

    INDEX
    Explanations

    kindness, kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.86
    re
    0.84
    ra
    0.84
     міста
    0.82
     vineyards
    0.80
    ا
    0.78
     标准
    0.76
     వర్
    0.76
     sals
    0.75
     adolescentes
    0.74
    POSITIVE LOGITS
    of
    1.00
    M
    0.89
    Y
    0.85
    P
    0.84
    含ま
    0.83
    holomorphic
    0.83
    ine
    0.82
    kind
    0.81
     kindness
    0.74
    Kind
    0.73
    Act Density 0.015%

    No Known Activations