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

    Neuronpedia

    INDEX
    Explanations

    discussions about accessibility and unique properties of products or concepts

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

    explaining cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skall
    -0.39
    kuuta
    -0.38
    setVerticalGroup
    -0.38
     liggen
    -0.38
    deelte
    -0.37
    Bism
    -0.37
     heiligen
    -0.37
     referrerpolicy
    -0.36
    ikian
    -0.35
     vieill
    -0.34
    POSITIVE LOGITS
    Искәрмәләр
    0.53
     kaarangay
    0.52
     հղումներ
    0.50
    haustible
    0.48
    Derbyniad
    0.47
     виправивши
    0.46
     ***!
    0.46
    fjspx
    0.45
     Accesat
    0.45
     autorytatywna
    0.45
    Act Density 0.027%

    No Known Activations