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

    Neuronpedia

    INDEX
    Explanations

    DF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -menu
    -0.07
    sb
    -0.06
    .Chart
    -0.06
    _suite
    -0.06
     hue
    -0.06
     nose
    -0.06
    ける
    -0.06
    unami
    -0.06
    Day
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    례
    0.07
     casualty
    0.07
     insist
    0.07
     loạt
    0.06
     BYU
    0.06
     kidneys
    0.06
     $("#"
    0.06
     Means
    0.06
     #"
    0.06
    landers
    0.06
    Act Density 0.002%

    No Known Activations