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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements and structuring symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TestBed
    -0.43
     principio
    -0.42
    bet
    -0.36
    红了
    -0.36
     ouv
    -0.36
     labios
    -0.36
     vaut
    -0.36
    StoryboardSegue
    -0.36
     dispara
    -0.36
    conse
    -0.36
    POSITIVE LOGITS
     rhestr
    0.55
    httphttps
    0.51
    msgTypes
    0.51
     picioare
    0.50
     îna
    0.49
     HFILL
    0.47
     Савезне
    0.47
     continúas
    0.46
    addContainerGap
    0.46
    copg
    0.46
    Act Density 0.003%

    No Known Activations