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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hazel
    -0.07
    139
    -0.06
     Bew
    -0.06
    $t
    -0.06
    高校
    -0.06
     precedent
    -0.06
    Nic
    -0.06
     gamble
    -0.06
    Path
    -0.06
     ков
    -0.06
    POSITIVE LOGITS
     '';
↵
    0.07
    unsupported
    0.06
    (QL
    0.06
     backlight
    0.06
    refund
    0.06
     "";
↵
    0.06
    -acre
    0.06
    OutOfBounds
    0.06
    lili
    0.06
     import
    0.06
    Act Density 0.004%

    No Known Activations