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

    Neuronpedia

    INDEX
    Explanations

    random generation/prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SDA
    -0.09
     coursework
    -0.08
     arbete
    -0.08
     Kristu
    -0.08
    Chel
    -0.08
     stof
    -0.08
     commented
    -0.08
    angstrom
    -0.08
     bua
    -0.08
     homolog
    -0.07
    POSITIVE LOGITS
    =random
    0.19
    随机
    0.18
     random
    0.17
    .Random
    0.17
     randomly
    0.17
    random
    0.16
    .random
    0.16
    _random
    0.16
    Random
    0.16
     случай
    0.15
    Act Density 0.046%

    No Known Activations