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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دون
    -0.08
    Ahead
    -0.07
     Pine
    -0.07
     cook
    -0.07
    嫫
    -0.07
    ledge
    -0.07
    redi
    -0.07
     siden
    -0.07
    aque
    -0.07
     cường
    -0.07
    POSITIVE LOGITS
    ﲤ
    0.07
    ʶ
    0.07
    مواف
    0.07
    0.07
    签约仪式
    0.07
     rapidly
    0.07
     assembly
    0.07
    _DGRAM
    0.07
    ⒠
    0.06
    []>↵
    0.06
    Act Density 0.002%

    No Known Activations