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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    geh
    -0.08
    --;
    -0.07
    _la
    -0.07
     ফর
    -0.07
    BY
    -0.07
    stackpath
    -0.07
     infusion
    -0.07
     la
    -0.07
    希
    -0.06
    /,
    -0.06
    POSITIVE LOGITS
     individuales
    0.14
     individually
    0.13
     individuais
    0.13
     individuele
    0.12
     individuelles
    0.12
     individual
    0.12
     individuel
    0.12
     individuelle
    0.12
     Individual
    0.12
    들을
    0.12
    Act Density 0.215%

    No Known Activations