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

    Neuronpedia

    INDEX
    Explanations

    references or citations to sources and figures in a document

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

    preceding references (e.g., see also)

    np_acts-logits-general · gemini-2.0-flash

    references and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.68
     autorytatywna
    -0.57
     الرياضيه
    -0.57
    RTEX
    -0.54
     hochzeit
    -0.53
    InjectAttribute
    -0.53
    ########.
    -0.52
     disambiguazione
    -0.51
    transQ
    -0.50
     estekak
    -0.50
    POSITIVE LOGITS
    see
    0.77
    See
    0.75
     see
    0.74
     See
    0.73
     lihat
    0.63
    siehe
    0.56
     below
    0.55
    Ikus
    0.54
    Siehe
    0.53
    Lihat
    0.53
    Act Density 0.539%

    No Known Activations