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

    Neuronpedia

    INDEX
    Explanations

    ultr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spanking
    -0.09
    hou
    -0.08
    bia
    -0.07
     groom
    -0.07
    jee
    -0.07
     EE
    -0.07
    ale
    -0.07
    nob
    -0.07
    BA
    -0.07
     spec
    -0.07
    POSITIVE LOGITS
     quadr
    0.11
     ultr
    0.09
     Ultr
    0.08
    .Mult
    0.07
    ighth
    0.06
     yerleştir
    0.06
    ltr
    0.06
    inflate
    0.06
    .ur
    0.06
    &(
    0.06
    Act Density 0.003%

    No Known Activations