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

    Neuronpedia

    INDEX
    Explanations

    grammatical words and descriptive words in German

    oai_token-act-pair · gemini-2.0-flash

    non-english languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ьаж
    -0.49
     Forever
    -0.47
    Else
    -0.46
    Turn
    -0.45
    turn
    -0.43
     Linger
    -0.41
    XtraEditors
    -0.40
    Forever
    -0.40
     Else
    -0.40
     Deja
    -0.39
    POSITIVE LOGITS
     bezeichneter
    0.86
    EDEFAULT
    0.72
     correctes
    0.71
    __*/
    0.68
    픈
    0.67
    קישורים
    0.65
    findpost
    0.64
    __":
    0.63
     berjudul
    0.62
    inguém
    0.61
    Act Density 0.092%

    No Known Activations