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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product specifications and characteristics

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

    versions and variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eintritt
    -0.48
     artesanato
    -0.43
     wahren
    -0.39
     Schichten
    -0.38
    uidado
    -0.37
     Wirklichkeit
    -0.36
     izay
    -0.34
     követ
    -0.34
     Identität
    -0.33
     biens
    -0.33
    POSITIVE LOGITS
     versione
    0.75
     version
    0.75
     Version
    0.68
     versions
    0.67
     variant
    0.66
     variants
    0.65
     Variants
    0.64
     versión
    0.63
    تقاوى
    0.63
     wers
    0.63
    Act Density 0.060%

    No Known Activations