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

    Neuronpedia

    INDEX
    Explanations

    towards Russia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     excuse
    0.42
     airways
    0.42
     पांडे
    0.40
     leash
    0.40
    },-\
    0.40
     Dog
    0.39
    Kal
    0.39
    Mak
    0.39
     تباہ
    0.39
     cage
    0.38
    POSITIVE LOGITS
    여
    0.54
    ན
    0.46
    며
    0.44
    ால்
    0.43
    올
    0.43
    ्य
    0.43
     אם
    0.43
    ａ
    0.43
    赏
    0.42
    కొ
    0.42
    Act Density 0.002%

    No Known Activations