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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in academic writing

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

    tables, figures, or supplementary materials

    np_acts-logits-general · gemini-2.0-flash

    reference and citation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BASEPATH
    -1.00
    badlogic
    -0.74
    formik
    -0.71
     deltaTime
    -0.66
    astify
    -0.65
     bParam
    -0.65
    存于互联网档案馆
    -0.65
     KeyError
    -0.65
     Betracht
    -0.63
     mattino
    -0.62
    POSITIVE LOGITS
    _
    0.68
    <eos>
    0.66
    loff
    0.51
    \_
    0.49
    __
    0.49
     Extern
    0.48
     _
    0.48
    IndentedString
    0.48
    External
    0.48
    ंदीखरीदारी
    0.47
    Act Density 1.062%

    No Known Activations