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

    Neuronpedia

    INDEX
    Explanations

    variable types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     어떤
    1.22
     Exponential
    1.18
     getUser
    1.18
     those
    1.17
     maxSum
    1.16
     Moist
    1.15
     Thé
    1.14
     các
    1.14
     vulgar
    1.11
     avoid
    1.11
    POSITIVE LOGITS
    of
    1.58
    to
    1.56
    info
    1.51
    dict
    1.50
    and
    1.49
    response
    1.46
    type
    1.46
    area
    1.44
    list
    1.44
    index
    1.43
    Act Density 0.207%

    No Known Activations