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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .checkBox
    -0.07
    ันย
    -0.07
    .styles
    -0.07
     معمول
    -0.06
     defeating
    -0.06
     Chrome
    -0.06
     celebrated
    -0.06
     Uran
    -0.06
     mount
    -0.06
     Gael
    -0.06
    POSITIVE LOGITS
    ensor
    0.06
     becoming
    0.06
    .toList
    0.06
    riters
    0.06
    Jordan
    0.06
     nymph
    0.06
     contrace
    0.06
    Being
    0.06
    Mary
    0.06
     hạ
    0.06
    Act Density 0.013%

    No Known Activations