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

    Neuronpedia

    INDEX
    Explanations

    references to physical appearance and descriptions of people or faces

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

    face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.43
     للمعارف
    -0.43
     незавершена
    -0.41
     المعيارى
    -0.41
     вікісторінку
    -0.38
    bitField
    -0.36
    Tikang
    -0.36
    doctype
    -0.35
     Ballroom
    -0.35
    CppCodeGen
    -0.35
    POSITIVE LOGITS
     face
    1.40
     Face
    1.27
    Face
    1.25
     faces
    1.19
    face
    1.16
     FACE
    1.11
     Gesicht
    1.08
     facial
    1.07
     ansik
    1.04
    FACE
    1.02
    Act Density 0.021%

    No Known Activations