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

    Neuronpedia

    INDEX
    Explanations

    actions completed or carried out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻞ
    0.38
    します
    0.33
    ediakan
    0.33
    ot
    0.30
    *
    0.29
    STRU
    0.28
    COPY
    0.28
    лях
    0.28
    лом
    0.28
    ०
    0.28
    POSITIVE LOGITS
     formed
    0.39
     annan
    0.37
     made
    0.36
     can
    0.36
     Rainbow
    0.35
     Astros
    0.34
    pesar
    0.34
    ल्यानंतर
    0.34
     dinosaur
    0.33
     system
    0.33
    Act Density 0.360%

    No Known Activations