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

    Neuronpedia

    INDEX
    Explanations

    Hebrew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     karşısında
    -0.07
    呼ば
    -0.06
    GeV
    -0.06
     duplicates
    -0.06
     теперь
    -0.06
     skipped
    -0.06
     Vertical
    -0.06
     sel
    -0.06
     gefunden
    -0.06
     triples
    -0.06
    POSITIVE LOGITS
     філ
    0.07
    carbon
    0.06
    ';↵↵↵↵
    0.06
    ition
    0.06
    커
    0.06
    '''
↵
    0.06
    =↵↵
    0.06
     сх
    0.06
     */
↵
↵
↵
    0.06
    argon
    0.06
    Act Density 0.003%

    No Known Activations