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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific texts

    np_max-act · gemini-2.0-flash

    suffixes

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     calendriers
    -0.56
     estekak
    -0.52
     Hybrid
    -0.52
     Erik
    -0.52
     المعيارى
    -0.52
     surla
    -0.50
    人民共和国
    -0.50
    wpi
    -0.49
    :^(
    -0.48
    EnableWeb
    -0.47
    POSITIVE LOGITS
    s
    0.87
     CreateTagHelper
    0.78
     consultato
    0.67
    ergies
    0.64
    saurus
    0.62
    sweise
    0.59
    ing
    0.58
    er
    0.58
    sburg
    0.56
    schild
    0.56
    Act Density 0.036%

    No Known Activations