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

    Neuronpedia

    INDEX
    Explanations

    hierarchical structures in data representation

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

    red, root, thread, remove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.42
    :✨
    -0.41
    irão
    -0.36
    ismet
    -0.35
     scratching
    -0.35
     trance
    -0.34
     Verlauf
    -0.33
     Einfluß
    -0.33
    叩
    -0.32
     spotless
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.61
     autorytatywna
    0.54
     '\\;'
    0.50
    UnitTesting
    0.50
    AndEndTag
    0.50
    SequentialGroup
    0.50
    SearchTree
    0.48
     Administrativna
    0.47
     subtree
    0.46
    OGND
    0.46
    Act Density 0.251%

    No Known Activations