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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and approaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLO
    -0.08
     erforderlich
    -0.07
     speichern
    -0.07
    lef
    -0.07
     cerr
    -0.07
     podrá
    -0.07
     gespeichert
    -0.07
    ुद
    -0.07
     nahezu
    -0.07
    ুদ
    -0.07
    POSITIVE LOGITS
     differently
    0.10
     tackling
    0.09
    慎
    0.09
     tackle
    0.09
     assuntos
    0.09
     abordagem
    0.08
     مسئ
    0.08
     نحو
    0.08
     vanuit
    0.08
     tackled
    0.08
    Act Density 0.026%

    No Known Activations