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

    Neuronpedia

    INDEX
    Explanations

    Joker, Pareto, toddlers, rise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    outheast
    0.42
     Departing
    0.39
    忏
    0.38
     dirig
    0.38
    embra
    0.37
     PGE
    0.37
    प्रधान
    0.37
     지구
    0.37
    十字
    0.37
     ಹಿ
    0.36
    POSITIVE LOGITS
    Digest
    0.42
    digest
    0.41
     cigar
    0.39
    have
    0.38
    Move
    0.38
     haven
    0.37
    甃
    0.37
     squash
    0.37
    bat
    0.37
     oaths
    0.37
    Act Density 0.000%

    No Known Activations