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

    Neuronpedia

    INDEX
    Explanations

    hells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    well
    -0.72
    hells
    -0.64
    Soorten
    -0.61
     vex
    -0.52
     Ashes
    -0.51
     Teufel
    -0.51
    roach
    -0.50
     slashing
    -0.49
     xrange
    -0.48
    htä
    -0.48
    POSITIVE LOGITS
     onResponse
    0.70
    AnimationsModule
    0.69
     Normdatei
    0.68
     تانيه
    0.61
    MessageTagHelper
    0.59
    expandindo
    0.59
    KommentareTeilen
    0.59
    scriptcase
    0.59
    :]:
    0.59
    ModelSerializer
    0.57
    Act Density 0.097%

    No Known Activations