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

    Neuronpedia

    INDEX
    Explanations

    FB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     While
    -0.07
     Parl
    -0.06
    "While
    -0.06
     лише
    -0.06
    School
    -0.06
     castle
    -0.06
    ajs
    -0.06
    "At
    -0.06
     meiden
    -0.06
    ​​
    -0.06
    POSITIVE LOGITS
    hydro
    0.07
    /hr
    0.07
    fed
    0.07
    vangst
    0.06
    حص
    0.06
     未
    0.06
    \View
    0.06
    дия
    0.05
     CommonModule
    0.05
     підготов
    0.05
    Act Density 0.008%

    No Known Activations