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

    Neuronpedia

    INDEX
    Explanations

    five videos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rourke
    0.41
    క్సి
    0.40
     някои
    0.40
     Ages
    0.40
     लची
    0.40
     photographing
    0.39
     Tourists
    0.39
    ladesh
    0.39
     కొన్ని
    0.39
    ArgsConstructor
    0.38
    POSITIVE LOGITS
    ブラ
    0.47
    特典
    0.43
    ޝ
    0.43
     misura
    0.42
    šenje
    0.42
    뻥
    0.42
    ה
    0.40
    헝
    0.40
    မှ
    0.39
    ਹ
    0.39
    Act Density 11.125%

    No Known Activations