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

    Neuronpedia

    INDEX
    Explanations

    numerical values and units associated with measurements or scaling

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

    Dimensions with "x" or "times"

    np_acts-logits-general · gemini-2.0-flash

    numbers and x for dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.97
    Hentet
    -0.95
     otomatig
    -0.90
    SequentialGroup
    -0.89
     propOrder
    -0.88
     autorytatywna
    -0.85
    WebVitals
    -0.84
    awtextra
    -0.84
     intptr
    -0.82
    httphttps
    -0.82
    POSITIVE LOGITS
    whatever
    0.60
     whatever
    0.57
     lipat
    0.56
     apapun
    0.48
    TIMES
    0.48
     magnification
    0.47
     Whatever
    0.47
     anybody
    0.46
    Whatever
    0.45
     tantos
    0.45
    Act Density 0.530%

    No Known Activations