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

    Neuronpedia

    INDEX
    Explanations

    patterns and parameters related to texture mapping in graphics

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

    "m" followed by specific characters

    np_acts-logits-general · gemini-2.0-flash

    m followed by symbols or at end of word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “
    -0.81
    a
    -0.71
    “
    -0.71
    o
    -0.66
    au
    -0.65
    at
    -0.63
    in
    -0.59
    ost
    -0.58
    y
    -0.57
     Correia
    -0.56
    POSITIVE LOGITS
     Bm
    1.17
     Xm
    1.01
     BBM
    0.97
     Dm
    0.96
     Amm
    0.95
     xm
    0.95
    getM
    0.93
     ESM
    0.92
     Rm
    0.90
    awtextra
    0.90
    Act Density 0.289%

    No Known Activations