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

    Neuronpedia

    INDEX
    Explanations

    groups of two or three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .OPEN
    -0.07
    >[↵
    -0.07
     ב
    -0.06
    .functions
    -0.06
     enctype
    -0.06
    _j
    -0.06
    Arguments
    -0.06
    Mountain
    -0.06
     культур
    -0.06
     badly
    -0.06
    POSITIVE LOGITS
     duo
    0.15
     trio
    0.14
     Duo
    0.11
     threesome
    0.09
     Trio
    0.09
    uo
    0.08
     Quart
    0.08
     quart
    0.08
     pair
    0.08
    955
    0.07
    Act Density 0.006%

    No Known Activations