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

    Neuronpedia

    INDEX
    Explanations

    sports-related statistics and outcomes

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

    direction or movement

    np_acts-logits-general · gemini-2.0-flash

    heading into or coming out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ofür
    -0.61
    ocl
    -0.48
    /******/
    -0.48
    ыгана
    -0.48
    Портали
    -0.47
    ække
    -0.46
    Referències
    -0.46
    jspx
    -0.45
     perdana
    -0.44
    hore
    -0.44
    POSITIVE LOGITS
     heading
    2.12
     entering
    2.06
     Entering
    1.76
    Heading
    1.75
    entering
    1.73
     Heading
    1.71
    Entering
    1.69
     going
    1.61
     coming
    1.56
    heading
    1.52
    Act Density 0.222%

    No Known Activations