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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation

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

    Let, Suppose, For

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ロウィン
    -1.03
     queſta
    -1.02
     $_(
    -1.00
    majánló
    -1.00
     ſind
    -0.98
     ddelwed
    -0.94
     ſch
    -0.93
     zwiſchen
    -0.92
    ſicht
    -0.91
     ainfi
    -0.90
    POSITIVE LOGITS
    \]
    1.23
    \[
    0.56
    ↵↵
    0.53
    </blockquote>
    0.52
    0
    0.45
    3
    0.45
    1
    0.44
    9
    0.43
    .
    0.43
     \]
    0.42
    Act Density 0.150%

    No Known Activations