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

    Neuronpedia

    INDEX
    Explanations

    experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    organ
    -0.07
     Mama
    -0.07
     Laur
    -0.07
    tcp
    -0.07
    apo
    -0.07
    lesia
    -0.07
    viar
    -0.07
     district
    -0.06
    ipl
    -0.06
    umba
    -0.06
    POSITIVE LOGITS
     experiments
    0.17
     experimentation
    0.12
     experiment
    0.12
     experimented
    0.11
     experimenting
    0.10
    periments
    0.10
     Experiment
    0.10
    实验
    0.08
    Experiment
    0.07
     Bugün
    0.07
    Act Density 0.019%

    No Known Activations