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

    Neuronpedia

    INDEX
    Explanations

    any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    1.03
    ς
    0.99
    ﻪ
    0.93
     единственный
    0.91
    ant
    0.89
    and
    0.89
    क्य
    0.89
    qtd
    0.89
    that
    0.88
    also
    0.88
    POSITIVE LOGITS
     GCSE
    1.21
     zipper
    1.16
     gradual
    1.13
     GDPR
    1.11
     denominator
    1.09
     semester
    1.08
     blockchain
    1.07
     callback
    1.05
     semiconductor
    1.05
     stencil
    1.05
    Act Density 0.172%

    No Known Activations