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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and specific entities in legal and scientific contexts

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

    pharmaceutics, gladiator, ponder, nureflex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zwiſchen
    -1.31
    ſicht
    -1.30
     ddelwed
    -1.30
     imagui
    -1.29
     queſta
    -1.28
    <unused52>
    -1.25
    <unused74>
    -1.25
    <unused51>
    -1.25
    <unused16>
    -1.25
    <unused41>
    -1.25
    POSITIVE LOGITS
    ↵↵
    0.50
     (
    0.46
     
    0.45
     and
    0.41
     The
    0.40
    ↵
    0.40
    (
    0.39
     etc
    0.38
    -
    0.36
    as
    0.35
    Act Density 1.903%

    No Known Activations