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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and performance metrics related to vehicle dynamics and control systems

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

    driving conditions safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     związku
    -0.38
    ništ
    -0.38
     universelle
    -0.37
     działal
    -0.37
     jahr
    -0.36
    Atentamente
    -0.35
     المعيارى
    -0.35
     démocr
    -0.35
     biologique
    -0.35
     biological
    -0.34
    POSITIVE LOGITS
     tiguan
    0.51
     SAFETY
    0.51
    Safety
    0.49
     safety
    0.45
    SAFETY
    0.44
    +#+#
    0.44
     Safety
    0.44
     bummer
    0.44
     braking
    0.43
     danger
    0.43
    Act Density 0.028%

    No Known Activations