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

    Neuronpedia

    INDEX
    Explanations

    bash commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ലോ
    0.74
    ленных
    0.71
    넴
    0.66
    ленные
    0.66
     বৈ
    0.65
    લો
    0.65
    iew
    0.65
    łuż
    0.64
    ланган
    0.63
    ifar
    0.62
    POSITIVE LOGITS
     sh
    0.63
    banking
    0.63
    ﺼ
    0.60
    த்துக்
    0.59
    rolled
    0.58
    敍
    0.57
    mash
    0.57
    బ్యా
    0.57
    ṣ
    0.56
    στή
    0.56
    Act Density 0.116%

    No Known Activations