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

    Neuronpedia

    INDEX
    Explanations

    or but and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कंज
    0.45
     pork
    0.40
    wearing
    0.39
    swarm
    0.39
     counselors
    0.38
     काउंसलिंग
    0.38
     prairies
    0.38
    counter
    0.38
    wort
    0.38
    neon
    0.37
    POSITIVE LOGITS
    而成
    0.43
    PartResult
    0.41
    義務
    0.40
    あらゆる
    0.40
    صی
    0.38
    ティ
    0.37
    ructural
    0.37
    レルギー
    0.37
    ――――
    0.37
    ტი
    0.37
    Act Density 0.000%

    No Known Activations