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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дія
    -0.07
     co
    -0.07
    ش
    -0.07
    とは
    -0.07
    ока
    -0.07
    щая
    -0.06
    ushing
    -0.06
    organ
    -0.06
    ucción
    -0.06
    住宅
    -0.06
    POSITIVE LOGITS
    Mods
    0.06
     Operations
    0.06
    Serializable
    0.06
    many
    0.06
    	filename
    0.06
    846
    0.06
    (nb
    0.06
     rely
    0.06
     many
    0.06
    mando
    0.06
    Act Density 0.008%

    No Known Activations