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

    Neuronpedia

    INDEX
    Explanations

    references to legal cases and academic titles

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

    Legal citations ("v." or "Dr.")

    np_acts-logits-general · gemini-2.0-flash

    legal citations (v.)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     her
    -0.60
     it
    -0.59
    ']],
    -0.56
     the
    -0.56
     or
    -0.56
     $
    -0.55
     format
    -0.55
     including
    -0.54
    '],$
    -0.53
     direct
    -0.53
    POSITIVE LOGITS
    .
    0.82
    .?
    0.79
     estekak
    0.72
    providedIn
    0.71
    . 
    0.65
    ./
    0.64
    .,
    0.64
    .!
    0.64
    .~
    0.64
     définiti
    0.64
    Act Density 0.457%

    No Known Activations