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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     low
    -1.24
     Low
    -1.18
     least
    -1.16
     LOW
    -1.15
     lowest
    -1.14
    Low
    -1.12
     Lowest
    -1.11
    least
    -1.11
    Lowest
    -1.05
    Least
    -1.05
    POSITIVE LOGITS
    h
    0.52
    tagHelperRunner
    0.43
    p
    0.41
    er
    0.40
    -
    0.38
    g
    0.37
    a
    0.33
    b
    0.32
     h
    0.31
    ger
    0.29
    Act Density 0.000%

    No Known Activations