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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters formatted in a matrix or table layout

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

    closing braces in technical text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]").
    -0.36
    llll
    -0.34
    "]).
    -0.33
    ']=$
    -0.30
     ')
    -0.30
     Secret
    -0.30
    QString
    -0.30
    }{{
    -0.30
    pyx
    -0.28
     Geheim
    -0.28
    POSITIVE LOGITS
    cccc
    1.33
    ccccc
    1.26
    ccc
    1.24
    ccccccc
    1.21
    cccccc
    1.21
    lccc
    1.16
    lcccccc
    0.97
    lcc
    0.95
    lccccc
    0.94
    cccccccc
    0.91
    Act Density 0.007%

    No Known Activations