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

    Neuronpedia

    INDEX
    Explanations

    province of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.64
    the
    0.55
     the
    0.48
    er
    0.47
    update
    0.46
     etc
    0.43
    مدينة
    0.42
    The
    0.42
     The
    0.41
     update
    0.41
    POSITIVE LOGITS
    เดียวกัน
    0.43
    ücksicht
    0.39
     sensibilité
    0.39
     مذکور
    0.39
     pêche
    0.39
     compreensão
    0.39
    氲
    0.38
     vocês
    0.37
     stesso
    0.36
    ونا
    0.36
    Act Density 0.009%

    No Known Activations