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

    Neuronpedia

    INDEX
    Explanations

    references to file validation and acceptable file extensions

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

    file extensions or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.59
    MLLoader
    -0.58
     myſelf
    -0.57
     faſt
    -0.57
    ſelf
    -0.57
     rospy
    -0.57
     Anſ
    -0.57
    ſelves
    -0.56
     himſelf
    -0.56
     Cæsar
    -0.56
    POSITIVE LOGITS
     lenguas
    0.36
    saraba
    0.32
     fler
    0.31
     identité
    0.30
     Branchen
    0.29
     ujednoznacz
    0.29
    styleUrls
    0.29
     clasificación
    0.28
     webu
    0.28
     povol
    0.28
    Act Density 0.026%

    No Known Activations