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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or uniqueness

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

    the only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.35
    ैल
    -0.35
     Incentives
    -0.35
    segno
    -0.34
    rases
    -0.34
     Years
    -0.34
    typ
    -0.33
     plutôt
    -0.33
    amat
    -0.33
    covo
    -0.33
    POSITIVE LOGITS
    satunya
    0.64
     einzigen
    0.59
     únicos
    0.59
    etlen
    0.52
    OCCURRED
    0.51
     únicas
    0.51
    Bibliograf
    0.51
     único
    0.51
     exception
    0.50
     ویکی‌پدی
    0.50
    Act Density 0.038%

    No Known Activations