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

    Neuronpedia

    INDEX
    Explanations

    discussions about legality, morality, and judgment in various contexts

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

    unusual qualifying conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.39
     outputStream
    -0.29
     since
    -0.28
    argout
    -0.27
    printLine
    -0.26
    EFIAPI
    -0.26
     TRE
    -0.26
    Hozzáférés
    -0.26
      
    -0.25
     Need
    -0.25
    POSITIVE LOGITS
    Personensuche
    0.68
     Infórmanos
    0.68
     виправивши
    0.66
     препратки
    0.65
     صوتيه
    0.61
     مشين
    0.58
    oa̍t
    0.56
     Administrativna
    0.55
    𖧹
    0.55
    iſchen
    0.53
    Act Density 0.103%

    No Known Activations