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

    Neuronpedia

    INDEX
    Explanations

    words describing the features of automobiles

    oai_token-act-pair · gemini-2.0-flash

    car body parts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.65
    encodeWith
    -0.59
     FontWeight
    -0.59
    getBean
    -0.58
     senhor
    -0.57
    RTEE
    -0.56
    blockList
    -0.52
     protoimpl
    -0.52
    Hentet
    -0.52
     typelib
    -0.51
    POSITIVE LOGITS
     fender
    0.64
     body
    0.59
     door
    0.58
    ManagedBean
    0.56
     panels
    0.56
     fenders
    0.55
     bumper
    0.54
     flare
    0.52
     Pardo
    0.52
    鈑
    0.52
    Act Density 2.535%

    No Known Activations