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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to data processing and organization

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

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.35
    use
    -0.31
     rispet
    -0.26
    clo
    -0.26
    private
    -0.26
     Pan
    -0.26
     r
    -0.26
    jn
    -0.25
    pan
    -0.25
    })));
    -0.25
    POSITIVE LOGITS
    Personendaten
    0.88
    Personensuche
    0.87
     незавершена
    0.78
     nahilalakip
    0.75
     يتيمه
    0.72
     فريبيس
    0.70
     betweenstory
    0.69
    Diweddarwch
    0.69
    TagMode
    0.68
    سطس
    0.67
    Act Density 0.235%

    No Known Activations