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

    Neuronpedia

    INDEX
    Explanations

    requests for feedback and communication from the audience

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

    code snippets and software usage

    np_acts-logits-general · gemini-2.0-flash

    our customers or other users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lacey
    -0.51
     času
    -0.51
    endfor
    -0.50
     autorytatywna
    -0.50
    PasswordEncoder
    -0.49
     latine
    -0.48
    ngdoc
    -0.48
     useDispatch
    -0.48
     Praze
    -0.48
     Latein
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.63
    évaluateur
    0.63
    Obrázky
    0.62
    parsedMessage
    0.61
     onlyOwner
    0.57
    oa̍t
    0.56
    Relevant
    0.56
     Normdatei
    0.55
     revan
    0.54
    !*\
    0.52
    Act Density 0.049%

    No Known Activations