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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issa
    -0.07
    annya
    -0.07
     irony
    -0.07
     politics
    -0.06
     Validate
    -0.06
     broker
    -0.06
    ět
    -0.06
    alter
    -0.06
    line
    -0.06
    яет
    -0.06
    POSITIVE LOGITS
    _UP
    0.07
     рекомендуется
    0.07
     mụn
    0.06
     心
    0.06
    身上
    0.06
     frauen
    0.06
    狗
    0.06
    NotExist
    0.06
    logan
    0.06
     nổi
    0.06
    Act Density 0.013%

    No Known Activations