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

    Neuronpedia

    INDEX
    Explanations

    references to annotations or decorators

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

    cal followed by code or math symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    -0.38
    _
    -0.37
     This
    -0.34
    This
    -0.34
    ั้น
    -0.32
     The
    -0.31
     trata
    -0.31
    데
    -0.30
    dev
    -0.30
     comprend
    -0.30
    POSITIVE LOGITS
     EconPapers
    0.90
     ſind
    0.84
     فريبيس
    0.80
    iſen
    0.73
    хьтан
    0.72
    arangay
    0.72
     Infórmanos
    0.71
    GEBURTSDATUM
    0.70
    нгред
    0.69
     ivelany
    0.68
    Act Density 0.017%

    No Known Activations