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

    Neuronpedia

    INDEX
    Explanations

    bug fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expansive
    0.35
     manipul
    0.34
     controla
    0.34
     carv
    0.34
     ساخته
    0.34
    chnen
    0.33
     произведения
    0.33
    juvant
    0.33
     Dyke
    0.33
     చేసుకోవ
    0.33
    POSITIVE LOGITS
     bug
    2.02
     Bug
    1.77
    Bug
    1.77
     bugs
    1.70
    bug
    1.67
    bugs
    1.48
     BUG
    1.44
     Bugs
    1.43
    BUG
    1.34
     reported
    1.23
    Act Density 0.028%

    No Known Activations