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

    Neuronpedia

    INDEX
    Explanations

    verbal communication and "Travis"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ch
    -0.65
    ir
    -0.62
    e
    -0.60
     nonverbal
    -0.59
    ips
    -0.59
    ik
    -0.56
    ek
    -0.54
    age
    -0.54
    ex
    -0.53
    ა
    -0.53
    POSITIVE LOGITS
     <>",
    0.70
    rungsseite
    0.68
    ocities
    0.67
    جغرافيا
    0.66
    省市镇
    0.64
    ConstraintMaker
    0.63
    Tembelea
    0.59
     كومونز
    0.59
     voren
    0.58
     peines
    0.57
    Act Density 0.008%

    No Known Activations