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

    Neuronpedia

    INDEX
    Explanations

    crisis text line and Trevor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udades
    0.39
    จุ
    0.39
    ricted
    0.38
    ﾏ
    0.35
    ierd
    0.35
     Bacterial
    0.35
    ichel
    0.35
     क्लीन
    0.35
    etok
    0.35
    umna
    0.34
    POSITIVE LOGITS
     Crisis
    0.56
     crisis
    0.54
    Crisis
    0.54
     Trevor
    0.49
    刑
    0.46
     treason
    0.42
     crises
    0.42
     tre
    0.41
     кризи
    0.41
    Tre
    0.40
    Act Density 0.051%

    No Known Activations