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

    Neuronpedia

    INDEX
    Explanations

    say the ending -ение

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    داشت
    -0.07
     irradi
    -0.07
    يب
    -0.06
     drv
    -0.06
     kwargs
    -0.06
    ково
    -0.06
     zemi
    -0.06
    ).'
    -0.06
    زيد
    -0.06
    ém
    -0.06
    POSITIVE LOGITS
     bounced
    0.07
     unmarried
    0.07
    _State
    0.07
     bisexual
    0.06
     Latino
    0.06
     державного
    0.06
    ヾ
    0.06
     Edison
    0.06
     indign
    0.06
     LGPL
    0.06
    Act Density 0.005%

    No Known Activations