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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and features of devices or systems

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

    Followed by "be" or indicating ease of use

    np_acts-logits-general · gemini-2.0-flash

    be followed by a modifier or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avantages
    -0.47
     sør
    -0.43
     warga
    -0.41
     plă
    -0.38
    readyState
    -0.38
    ضح
    -0.38
     Mittel
    -0.37
    бов
    -0.37
    rut
    -0.37
     gmina
    -0.36
    POSITIVE LOGITS
    tvguidetime
    1.02
     GenerationType
    0.95
    IsMutable
    0.93
    parsedMessage
    0.85
     дописавши
    0.81
     Signalez
    0.81
    :✨
    0.80
    Tembelea
    0.80
     Easily
    0.79
     مرئيه
    0.78
    Act Density 0.195%

    No Known Activations