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

    Neuronpedia

    INDEX
    Explanations

    .from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Greenwood
    -0.09
    puestas
    -0.08
    {
↵
    -0.08
     Sacramento
    -0.07
    iosamente
    -0.07
    dans
    -0.07
     Psychological
    -0.07
     gå
    -0.07
     psychological
    -0.07
    Utils
    -0.07
    POSITIVE LOGITS
    .from
    0.09
    -from
    0.09
    _from
    0.08
     থেকেই
    0.08
    పు
    0.07
    不了
    0.07
    _From
    0.07
    คำ
    0.07
    ची
    0.07
    తెల
    0.07
    Act Density 0.003%

    No Known Activations