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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the letter 'r' in various forms

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

    r sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getStatusCode
    -0.63
    ειτουργ
    -0.57
    pense
    -0.54
    いけない
    -0.54
     Neuf
    -0.53
     Gillespie
    -0.53
     Chio
    -0.52
    consola
    -0.52
    üche
    -0.52
    </thead>
    -0.52
    POSITIVE LOGITS
    r
    1.76
     r
    1.30
    rr
    0.93
    getR
    0.89
    R
    0.86
    rA
    0.75
    р
    0.75
    rs
    0.74
    rB
    0.73
    rrr
    0.71
    Act Density 0.068%

    No Known Activations