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

    Neuronpedia

    INDEX
    Explanations

    Spanish and Portuguese

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Around
    -0.06
     vacations
    -0.06
    ować
    -0.06
     fi
    -0.06
    ��
    -0.06
    한다
    -0.05
     etiquette
    -0.05
    ується
    -0.05
    両
    -0.05
     холодиль
    -0.05
    POSITIVE LOGITS
    _misc
    0.07
     Decor
    0.07
     �
    0.07
    odox
    0.07
     Peggy
    0.07
     Podcast
    0.07
    (socket
    0.06
     ตำ
    0.06
     merc
    0.06
     Berry
    0.06
    Act Density 0.010%

    No Known Activations