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

    Neuronpedia

    INDEX
    Explanations

    side by side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devenir
    0.54
     doctora
    0.50
     anest
    0.47
    жидан
    0.46
    হৃত
    0.46
     persone
    0.45
     pessoa
    0.45
     univer
    0.45
     lucrat
    0.45
     commutes
    0.44
    POSITIVE LOGITS
    法
    0.45
    杉
    0.44
    ೋಪ
    0.43
    scht
    0.41
    六
    0.41
    绕
    0.41
     আইন
    0.40
     その他
    0.40
    DEFGHI
    0.40
    II
    0.39
    Act Density 0.028%

    No Known Activations