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
    Set
    -0.07
     Mohamed
    -0.07
    否则
    -0.07
    ム
    -0.07
    <dim
    -0.07
     넘
    -0.07
    补齐
    -0.07
    扣
    -0.06
     encrypted
    -0.06
    oops
    -0.06
    POSITIVE LOGITS
    传销
    0.09
    pirit
    0.08
    .Points
    0.08
     ela
    0.07
     Bloss
    0.07
     PTS
    0.07
    ardo
    0.07
     remarks
    0.07
     noss
    0.06
     esper
    0.06
    Act Density 0.066%

    No Known Activations