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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and teams

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

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.72
     geweſen
    -0.68
    ſſung
    -0.67
    [@BOS@]
    -0.67
    <unused41>
    -0.67
    <unused74>
    -0.67
    <unused80>
    -0.67
    <unused68>
    -0.67
    <unused3>
    -0.67
    <unused51>
    -0.67
    POSITIVE LOGITS
    <?
    0.28
    EClass
    0.25
     actionPerformed
    0.25
    ().__
    0.24
    less
    0.24
    })`
    0.24
    setCharacter
    0.24
    ok
    0.24
     onAnimation
    0.23
     Wikiseite
    0.23
    Act Density 0.041%

    No Known Activations