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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilty
    -0.07
    犯罪
    -0.07
    -feature
    -0.07
    Those
    -0.06
    Viol
    -0.06
    Choosing
    -0.06
     arisen
    -0.06
    Maximum
    -0.06
    STOP
    -0.06
     mart
    -0.06
    POSITIVE LOGITS
     發
    0.07
    тик
    0.07
    (per
    0.06
    活動
    0.06
     aaa
    0.06
    .named
    0.06
    ソ
    0.06
     віт
    0.06
     vog
    0.06
     соци
    0.06
    Act Density 0.041%

    No Known Activations