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

    Neuronpedia

    INDEX
    Explanations

    name + descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arily
    0.37
    =============
    0.37
     headspace
    0.37
    在使用
    0.36
    ===============
    0.35
    ոն
    0.35
    ailable
    0.34
    ward
    0.34
    dule
    0.34
    ション
    0.34
    POSITIVE LOGITS
    Black
    0.45
     Due
    0.41
    缭
    0.41
     Black
    0.38
    ;")
    0.38
    ủy
    0.38
    丫
    0.38
    ѓ
    0.38
     reductase
    0.36
     okresie
    0.36
    Act Density 0.018%

    No Known Activations