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

    Neuronpedia

    INDEX
    Explanations

    references to application programming or technical specifications

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forças
    -0.50
     irmã
    -0.46
    tidaknya
    -0.43
     sesama
    -0.41
     encont
    -0.41
    visející
    -0.40
     olvidado
    -0.40
     disfr
    -0.40
     znale
    -0.39
     heridos
    -0.39
    POSITIVE LOGITS
     houſe
    0.81
     Houſe
    0.68
    WithIOException
    0.66
     myſelf
    0.60
     fubject
    0.59
     AMP
    0.59
     cyclic
    0.57
     Apps
    0.56
    ſelf
    0.56
     faſt
    0.55
    Act Density 0.000%

    No Known Activations