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

    Neuronpedia

    INDEX
    Explanations

    inquiries about definitions, rights, and responsibilities

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

    determining what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nadzieję
    -0.56
    GTCX
    -0.54
     yalnızca
    -0.52
     nakalista
    -0.52
    WriteTagHelper
    -0.52
     bandoulière
    -0.50
     capuz
    -0.50
    SequentialGroup
    -0.50
     ब्रेकडाउन
    -0.50
     parlato
    -0.49
    POSITIVE LOGITS
     pepe
    0.45
     corti
    0.42
     Doha
    0.41
    ]='\
    0.39
     ویکی‌پدیا
    0.37
    =?
    0.36
    tanleria
    0.36
     Represent
    0.36
     REALLY
    0.36
     neop
    0.35
    Act Density 0.043%

    No Known Activations