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

    Neuronpedia

    INDEX
    Explanations

    parenthetical references or citations

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

    specifications or continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    -0.33
    <
    -0.27
    　
    -0.26
     encuentro
    -0.26
    ↵
    -0.25
    “
    -0.24
     lanza
    -0.24
     embaj
    -0.24
    ↵↵
    -0.23
     ejecutivo
    -0.23
    POSITIVE LOGITS
    ScopeManager
    1.05
    niſſe
    1.03
    <unused41>
    1.02
    ſſung
    1.02
    <unused14>
    1.02
    [@BOS@]
    1.02
    <unused16>
    1.01
    <unused23>
    1.01
    <unused8>
    1.01
    <unused3>
    1.01
    Act Density 0.094%

    No Known Activations