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

    Neuronpedia

    INDEX
    Explanations

    crisis text line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mention
    0.42
    魧
    0.41
    撫
    0.39
    pond
    0.39
     наход
    0.39
     مربع
    0.38
     аромат
    0.38
    र्चे
    0.38
    orod
    0.38
    0.38
    POSITIVE LOGITS
     transported
    0.38
     Human
    0.38
     seriously
    0.36
    HUM
    0.35
     human
    0.35
     bark
    0.35
     rings
    0.35
     inspections
    0.35
     Bary
    0.35
     Fasc
    0.34
    Act Density 0.008%

    No Known Activations