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

    Neuronpedia

    INDEX
    Explanations

    moral justification or progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вары
    0.54
    Like
    0.47
    ᅨ
    0.47
    ᅯ
    0.46
    ոն
    0.45
    virtual
    0.45
    Static
    0.43
    urity
    0.41
    া
    0.41
    er
    0.41
    POSITIVE LOGITS
     Bugünkü
    0.47
     dà
    0.46
     precarious
    0.45
    帼
    0.44
     incó
    0.43
     بی
    0.43
     البدايه
    0.43
     uncomfortable
    0.42
     شويه
    0.42
    ductor
    0.41
    Act Density 0.000%

    No Known Activations