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

    Neuronpedia

    INDEX
    Explanations

    code snippets or elements related to programming constructs and structures

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

    code structure and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.40
    ロウィン
    -1.34
    iſchen
    -1.33
    ſſung
    -1.31
    iſche
    -1.28
    <unused41>
    -1.27
    <unused74>
    -1.27
    <unused14>
    -1.27
    <unused8>
    -1.27
    [@BOS@]
    -1.27
    POSITIVE LOGITS
    hline
    0.63
    (
    0.58
    ↵↵
    0.58
    0
    0.57
    In
    0.55
    If
    0.50
    A
    0.50
    if
    0.50
    1
    0.50
    As
    0.48
    Act Density 0.020%

    No Known Activations