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

    Neuronpedia

    INDEX
    Explanations

    typedef, transportation, company, arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.53
    A
    0.53
    U
    0.52
    S
    0.52
    ry
    0.50
     gift
    0.48
    <
    0.48
    gift
    0.47
    G
    0.45
    na
    0.45
    POSITIVE LOGITS
    zovaniyu
    0.54
     NSTX
    0.52
     ABSOR
    0.50
    жий
    0.49
     亠
    0.49
    苚
    0.49
    ತರ
    0.48
     ROWS
    0.47
     ArrayRef
    0.47
     తెలు
    0.46
    Act Density 0.004%

    No Known Activations