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

    Neuronpedia

    INDEX
    Explanations

    other than, different types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    苼
    0.28
     invincible
    0.27
     settlers
    0.26
     partido
    0.25
     ይህ
    0.25
     каттоо
    0.25
    琿
    0.25
    sbParams
    0.25
     sieve
    0.24
    ječ
    0.24
    POSITIVE LOGITS
    ;
    0.35
    ?
    0.34
    ע
    0.31
    -
    0.30
    !
    0.30
    :
    0.30
    0.29
    But
    0.28
    ो
    0.28
    A
    0.27
    Act Density 0.077%

    No Known Activations