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

    Neuronpedia

    INDEX
    Explanations

    trained on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mangle
    0.37
    ánh
    0.37
    getPopulation
    0.36
     wą
    0.35
     operated
    0.35
     gone
    0.34
     pest
    0.34
     gått
    0.34
    গরের
    0.33
    dött
    0.33
    POSITIVE LOGITS
    Verse
    0.42
    .}$
    0.38
    .')
    0.37
    务
    0.37
     corrispond
    0.37
    Aquí
    0.37
     minum
    0.37
    为您
    0.36
    Neces
    0.36
    Funcion
    0.36
    Act Density 0.002%

    No Known Activations