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

    Neuronpedia

    INDEX
    Explanations

    technical terms and details related to railway systems and operations

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

    Starts a new turn or follows digits

    np_acts-logits-general · gemini-2.0-flash

    locomotives, renamed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.53
     faſt
    -0.42
     purpoſe
    -0.41
     ſtand
    -0.41
     ſmall
    -0.41
     Anfitrión
    -0.39
     ويكيميديا
    -0.37
    SdkVersion
    -0.37
     ſta
    -0.36
     juſt
    -0.36
    POSITIVE LOGITS
     صوتيه
    0.62
    RenderAtEndOf
    0.56
    AndEndTag
    0.52
     ConstraintSet
    0.50
     محفوظة
    0.48
    SequentialGroup
    0.48
     externs
    0.45
    WriteTagHelper
    0.43
    nias
    0.43
     locomotives
    0.43
    Act Density 0.249%

    No Known Activations