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

    Neuronpedia

    INDEX
    Explanations

    patterns and elements related to coding and programming

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

    Capital letters, often initials

    np_acts-logits-general · gemini-2.0-flash

    D.R. or C.R. abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    archiviato
    -0.62
     Neves
    -0.62
     Campion
    -0.61
    encies
    -0.60
    hilfe
    -0.59
    amation
    -0.59
    комму
    -0.58
    eat
    -0.57
    ]**
    -0.57
     Hermitage
    -0.57
    POSITIVE LOGITS
    RRRR
    1.01
    r
    0.95
    er
    0.89
    hr
    0.88
    rrr
    0.86
    rrrrr
    0.86
    R
    0.84
    rr
    0.83
    rrrr
    0.81
    ER
    0.80
    Act Density 0.599%

    No Known Activations