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

    Neuronpedia

    INDEX
    Explanations

    excellent performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कठिना
    0.40
    椅子
    0.39
    िलों
    0.38
     खींचो
    0.38
    一致
    0.37
    困难
    0.37
    閫
    0.37
    たくさん
    0.37
    風呂
    0.37
     autoclave
    0.37
    POSITIVE LOGITS
     Ser
    0.40
    dSample
    0.40
     proved
    0.40
     presentes
    0.40
    કોટ
    0.39
    েত্রে
    0.38
    쳥
    0.38
     pequeña
    0.37
     observed
    0.37
     pertinent
    0.37
    Act Density 0.001%

    No Known Activations