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

    Neuronpedia

    INDEX
    Explanations

    man

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecture
    -0.07
    sein
    -0.07
    \<
    -0.07
    .SetValue
    -0.07
    ungen
    -0.07
    עביר
    -0.07
     detach
    -0.07
    achievement
    -0.07
    (visible
    -0.07
     numero
    -0.06
    POSITIVE LOGITS
     Bair
    0.06
    是一种
    0.06
     JW
    0.06
    بدا
    0.06
     zza
    0.06
     букв
    0.06
    _gt
    0.06
    答卷
    0.06
    *R
    0.06
    entialAction
    0.06
    Act Density 0.045%

    No Known Activations