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

    Neuronpedia

    INDEX
    Explanations

    self-care and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ￣
    0.77
    ইর
    0.68
     Aless
    0.67
     относи
    0.67
     ग्वालियर
    0.65
     নির্বাচনী
    0.64
    复
    0.64
    ǔ
    0.64
    之类的
    0.63
    Russian
    0.62
    POSITIVE LOGITS
     Palestine
    0.76
    لسط
    0.76
    elp
    0.74
     PA
    0.70
    claim
    0.66
     Pott
    0.65
     Jen
    0.63
     pleas
    0.63
    cline
    0.62
     rockets
    0.62
    Act Density 0.074%

    No Known Activations