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

    Neuronpedia

    INDEX
    Explanations

    mary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UTC
    -0.07
    ;|
    -0.07
    Sound
    -0.06
     jeans
    -0.06
     préc
    -0.06
     subclasses
    -0.06
     swingers
    -0.06
     Notre
    -0.06
     توانید
    -0.06
     NM
    -0.06
    POSITIVE LOGITS
    expanded
    0.07
    _binary
    0.07
     house
    0.06
     plenty
    0.06
     frequ
    0.06
     Blacks
    0.06
     benchmark
    0.06
    指定
    0.06
     Mohammad
    0.06
     survey
    0.06
    Act Density 0.002%

    No Known Activations