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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     здійснення
    -0.06
    蜘蛛
    -0.06
    oque
    -0.06
    Android
    -0.06
     쪽
    -0.06
    めた
    -0.06
     Vi
    -0.06
    istream
    -0.05
    去了
    -0.05
     Shaw
    -0.05
    POSITIVE LOGITS
    hoot
    0.07
     pedest
    0.07
    �
    0.07
     pys
    0.06
    levation
    0.06
    条件
    0.06
     trusting
    0.06
    <string
    0.06
    sa
    0.06
    ceed
    0.06
    Act Density 0.000%

    No Known Activations