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

    Neuronpedia

    INDEX
    Explanations

    passwords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teen
    -0.07
    731
    -0.07
     Пол
    -0.06
     شر
    -0.06
     �
    -0.06
    651
    -0.06
     master
    -0.06
    现代
    -0.06
    -find
    -0.06
     trust
    -0.06
    POSITIVE LOGITS
    ้าช
    0.08
     Agile
    0.07
     Antoine
    0.07
    .vue
    0.06
     відпов
    0.06
    ….↵↵
    0.06
        ↵
    0.06
     makeStyles
    0.06
    WAR
    0.06
    disable
    0.06
    Act Density 0.013%

    No Known Activations