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

    Neuronpedia

    INDEX
    Explanations

    descriptive words followed by related nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -/
    1.24
    -(
    1.20
    -,
    1.19
     (=
    1.15
    ؛
    1.11
    (
    1.08
    (=
    1.05
    ;
    1.04
    ("\
    1.02
    、
    1.02
    POSITIVE LOGITS
     wanita
    1.20
     nbsp
    1.19
     crochet
    1.17
     yoga
    1.14
     minecraft
    1.12
     mediterranean
    1.10
     mariage
    1.09
     wikipedia
    1.08
     autism
    1.08
     iphone
    1.07
    Act Density 0.198%

    No Known Activations