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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and symbols in code or markup

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

    Square brackets surrounding a three-letter abbreviation

    np_acts-logits-general · gemini-2.0-flash

    Source: "{", "[sec:", "[lem:", "[fig:", "im(", and "ker("

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AAAAAAAAAAAAAAAA
    -0.59
     television
    -0.58
     iſt
    -0.56
     rodríguez
    -0.55
     beziehungs
    -0.55
    onenumber
    -0.53
     Monfieur
    -0.53
    HHHHHHHH
    -0.53
     kilogram
    -0.53
    wiſe
    -0.52
    POSITIVE LOGITS
    aarrggbb
    0.87
     Univ
    0.86
    Univ
    0.82
    ereq
    0.78
     req
    0.75
     Utd
    0.74
     Assn
    0.73
     ppl
    0.73
     probs
    0.73
     Dems
    0.73
    Act Density 1.814%

    No Known Activations