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

    Neuronpedia

    INDEX
    Explanations

    code setup commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acağ
    0.40
     sesuatu
    0.40
     şeyi
    0.38
     swój
    0.36
    ிருக்கு
    0.36
    lonitrile
    0.35
     membuka
    0.35
    ittelt
    0.35
    ELEASE
    0.34
     Swezey
    0.34
    POSITIVE LOGITS
    、
    0.63
    ,
    0.53
     and
    0.50
    ;
    0.46
    and
    0.45
    _,
    0.45
    #,
    0.45
    And
    0.45
     или
    0.44
     ,
    0.44
    Act Density 0.033%

    No Known Activations