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

    Neuronpedia

    INDEX
    Explanations

    risks and rewards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sly
    -0.07
     Kramer
    -0.06
    862
    -0.06
    _exam
    -0.06
     entrance
    -0.06
     hiding
    -0.06
    (bl
    -0.06
     gcc
    -0.06
     müşteri
    -0.06
    (handles
    -0.06
    POSITIVE LOGITS
    nač
    0.06
     EVER
    0.06
    UTF
    0.06
    itung
    0.06
    Type
    0.06
    HELP
    0.06
     Markup
    0.06
    tingham
    0.06
     occurred
    0.06
    ../../
    0.06
    Act Density 0.073%

    No Known Activations