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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "%
    -0.07
    土
    -0.07
    Uint
    -0.07
    imest
    -0.07
     UINT
    -0.07
     nec
    -0.07
    UINT
    -0.07
    杭
    -0.07
     Ey
    -0.07
     Utt
    -0.06
    POSITIVE LOGITS
    大跌
    0.08
    deaux
    0.08
     jurors
    0.07
    确实是
    0.07
    .Reporting
    0.07
     starvation
    0.07
     Couples
    0.07
    嚆
    0.07
     disparate
    0.07
    𬶟
    0.07
    Act Density 0.004%

    No Known Activations