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

    Neuronpedia

    INDEX
    Explanations

    references to identifiers or codes in academic or technical contexts

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

    `][` and `@` sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geweest
    -0.52
     raiſ
    -0.51
     poffible
    -0.50
     fubject
    -0.48
     Autorisations
    -0.47
    出版年
    -0.47
     noqa
    -0.46
     chofe
    -0.45
     Autorizaciones
    -0.45
    tagHelperRunner
    -0.44
    POSITIVE LOGITS
    ][
    1.17
    ()][
    1.02
    [][
    0.90
    ]][
    0.79
    )][
    0.77
    ][$
    0.71
     ][
    0.70
     }{@
    0.69
     bezeichneter
    0.61
    +][
    0.54
    Act Density 0.026%

    No Known Activations