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

    Neuronpedia

    INDEX
    Explanations

    code definitions, specifically related to constants and functions

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

    type Module, approval the, Galα antigen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.38
     iprot
    -0.35
    Autoritní
    -0.35
    scriptcase
    -0.33
     reputación
    -0.32
     Signalez
    -0.31
     económica
    -0.31
    WriteBarrier
    -0.31
    jší
    -0.31
     pluie
    -0.31
    POSITIVE LOGITS
     const
    0.90
    rungsseite
    0.61
     Fizz
    0.55
    ntax
    0.55
     Progress
    0.54
     Constable
    0.54
     Aran
    0.53
     Motto
    0.52
    ubar
    0.52
     Const
    0.52
    Act Density 0.000%

    No Known Activations