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
     recur
    -0.07
    [-
    -0.07
     proyectos
    -0.07
     chữ
    -0.07
     축
    -0.07
    ครอบ
    -0.07
     расч
    -0.06
    categoria
    -0.06
     clinging
    -0.06
     plais
    -0.06
    POSITIVE LOGITS
    Howard
    0.06
    well
    0.06
     firefox
    0.06
     ★
    0.06
     Established
    0.06
    authenticated
    0.06
    Improved
    0.06
    níkem
    0.06
    .fold
    0.06
    …"
    0.06
    Act Density 0.000%

    No Known Activations