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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    魂
    -0.07
    🐷
    -0.07
    ⁽
    -0.07
    🥺
    -0.07
     łaz
    -0.07
    Mis
    -0.07
    吸毒
    -0.06
    sk
    -0.06
     $('
    -0.06
    Required
    -0.06
    POSITIVE LOGITS
    ecera
    0.08
    .contains
    0.07
    bersome
    0.07
    ED
    0.07
    本身
    0.07
     Liberia
    0.07
     mogul
    0.07
     Kurdish
    0.07
     Rivers
    0.07
    等等
    0.07
    Act Density 0.367%

    No Known Activations