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

    Neuronpedia

    INDEX
    Explanations

    references to "cars" and/or driving.

    oai_token-act-pair · gemini-2.0-flash

    Vehicles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ford
    -0.56
     Honda
    -0.53
     Nissan
    -0.49
     VW
    -0.49
     Mac
    -0.48
     Toyota
    -0.48
    illado
    -0.48
     Haw
    -0.47
     Cor
    -0.47
     maison
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.83
    OGND
    0.77
     himo
    0.72
    adaptiveStyles
    0.66
     nahilalakip
    0.63
     المعيارى
    0.63
    Portale
    0.60
    BagConstraints
    0.60
    SBATCH
    0.59
    0.58
    Act Density 0.674%

    No Known Activations