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

    Neuronpedia

    INDEX
    Explanations

    technical programming syntax and identifiers

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

    Code snippets with arrows, parentheses, or quotes

    np_acts-logits-general · gemini-2.0-flash

    field names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.82
     betweenstory
    -0.75
     ब्रेकडाउन
    -0.73
    adaptiveStyles
    -0.72
     ujednoznacz
    -0.69
    <unused28>
    -0.68
    <unused52>
    -0.68
    <unused23>
    -0.68
    <unused14>
    -0.68
    <unused17>
    -0.68
    POSITIVE LOGITS
    原始内容存档于
    0.34
    ?>">
    0.23
     aina
    0.23
     godine
    0.22
    zarchiwizowane
    0.22
    SequentialGroup
    0.21
    ↵↵
    0.21
     cobran
    0.20
    基础
    0.20
     mens
    0.20
    Act Density 0.307%

    No Known Activations