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

    Neuronpedia

    INDEX
    Explanations

    repeated symbols or formatting markers typically used for delineation

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

    lines of dashes and asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    -0.51
    afficheront
    -0.45
    ERC
    -0.44
    pC
    -0.43
    greenrobot
    -0.43
    kjø
    -0.42
     églises
    -0.42
    ा
    -0.42
    PSC
    -0.41
     Budaya
    -0.41
    POSITIVE LOGITS
    *****
    0.73
     *****
    0.67
    -----
    0.65
    —–
    0.64
     -----
    0.63
    //-----
    0.63
     Worcestershire
    0.61
     =====
    0.56
     pstmt
    0.55
    ………..
    0.55
    Act Density 0.051%

    No Known Activations