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

    Neuronpedia

    INDEX
    Explanations

    crisis support services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    0.74
    ంగా
    0.73
    ،
    0.73
    ו
    0.71
    าย
    0.71
    و
    0.70
    ти
    0.63
    ाम
    0.63
    ات
    0.63
    ونه
    0.63
    POSITIVE LOGITS
    TE
    0.80
    do
    0.72
    TS
    0.72
    rd
    0.71
     lire
    0.71
    rt
    0.67
    SC
    0.65
    dr
    0.65
    GE
    0.63
    rr
    0.63
    Act Density 0.026%

    No Known Activations