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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ഖ
    -0.07
     Often
    -0.07
     vig
    -0.07
    astered
    -0.07
     känna
    -0.07
     Hinter
    -0.07
    _STAGE
    -0.07
    ालित
    -0.07
    _series
    -0.07
    睡
    -0.07
    POSITIVE LOGITS
     curs
    0.08
    505
    0.08
     vre
    0.08
     curve
    0.07
     Respublikas
    0.07
    essi
    0.07
     sebi
    0.07
     conditioners
    0.07
     össze
    0.07
     Prezidenti
    0.07
    Act Density 0.000%

    No Known Activations