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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and specific notation used in equations or proofs

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

    mathematical expressions with braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconn
    -0.46
     perpé
    -0.45
     LCCN
    -0.45
     cardiaque
    -0.45
    ième
    -0.45
     religieuses
    -0.44
    ampilan
    -0.44
          
    -0.43
    Tracce
    -0.43
     فريبيس
    -0.43
    POSITIVE LOGITS
    \}
    2.03
    \}\
    1.16
     \}
    1.15
    )\}
    1.09
     $\}$
    1.07
    }\}
    1.00
    \},
    0.95
    \}.
    0.93
    \}$
    0.93
    \}}
    0.88
    Act Density 0.046%

    No Known Activations