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

    Neuronpedia

    INDEX
    Explanations

    elements related to traffic and driving experiences

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

    associated with reversing direction

    np_acts-logits-general · gemini-2.0-flash

    forward and backward movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhestr
    -0.74
    älde
    -0.56
    τύ
    -0.54
    AutoScaleMode
    -0.53
     createState
    -0.53
     getItemCount
    -0.53
    sizeCache
    -0.52
     disambiguazione
    -0.52
    исленность
    -0.52
    Necesito
    -0.52
    POSITIVE LOGITS
     reverse
    1.84
     Reverse
    1.59
    reverse
    1.55
    Reverse
    1.52
     reversed
    1.47
     reversing
    1.35
     backwards
    1.32
     inverse
    1.31
    reversed
    1.28
     return
    1.27
    Act Density 0.356%

    No Known Activations