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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and library import statements

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

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.53
    ↵
    -0.43
    A
    -0.41
    </em>
    -0.37
    ,
    -0.37
    O
    -0.37
    })
    -0.36
    I
    -0.36
    a
    -0.35
    1
    -0.35
    POSITIVE LOGITS
     kasarigan
    1.00
     queſta
    0.88
    iſche
    0.86
    <unused41>
    0.86
    <unused3>
    0.85
    <pad>
    0.85
    <unused52>
    0.85
    ſſung
    0.85
    ſicht
    0.85
    [@BOS@]
    0.85
    Act Density 0.006%

    No Known Activations