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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shirt
    -0.07
     незалеж
    -0.07
     arrive
    -0.07
    其他
    -0.06
     grandfather
    -0.06
     Turtle
    -0.06
    ounced
    -0.06
     literature
    -0.06
    .round
    -0.06
     mysql
    -0.06
    POSITIVE LOGITS
     eapply
    0.08
     "["
    0.07
              ↵
    0.06
     Sally
    0.06
     –↵
    0.06
    cao
    0.06
     […]↵
    0.06
     sprav
    0.06
    /↵↵↵
    0.06
    ､:
    0.06
    Act Density 0.016%

    No Known Activations