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

    Neuronpedia

    INDEX
    Explanations

    closing braces and other punctuation related to code structure

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

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.54
    SceneManagement
    -0.51
    tonode
    -0.48
    Ӕ
    -0.47
    extAlignment
    -0.47
    Читати
    -0.46
     forState
    -0.46
    ByExample
    -0.45
     betweenstory
    -0.45
     Meksiku
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.55
    classmethod
    0.48
    RTHOOK
    0.44
    Autowired
    0.39
    nodoc
    0.37
    +:+
    0.37
     initComponents
    0.36
     Tarif
    0.35
     said
    0.35
    SPATH
    0.34
    Act Density 0.001%

    No Known Activations