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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and numeric values related to parameters and data fields

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    source._repeatedStringPiece

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.74
    rusty
    -0.70
     Carroll
    -0.69
     Kenny
    -0.67
     Rusty
    -0.66
     Downey
    -0.66
     Clarence
    -0.66
     Salty
    -0.65
     dacia
    -0.64
     Pagoda
    -0.63
    POSITIVE LOGITS
     Taub
    0.63
     Bradbury
    0.59
     Piper
    0.58
    beginTransaction
    0.58
     Berg
    0.58
     BRUN
    0.58
     Wilbur
    0.58
     DF
    0.56
     Bourgoin
    0.55
     OMITBAD
    0.55
    Act Density 0.785%

    No Known Activations