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

    Neuronpedia

    INDEX
    Explanations

    plead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sample
    -0.07
    -0.07
    "data
    -0.07
     demonstrates
    -0.07
    	admin
    -0.06
     md
    -0.06
    是我国
    -0.06
     �
    -0.06
     liver
    -0.06
    CLU
    -0.06
    POSITIVE LOGITS
    Ｂ
    0.07
     brid
    0.07
    以往
    0.07
    REC
    0.07
    など
    0.06
     pointing
    0.06
    larından
    0.06
     обращ
    0.06
     계속
    0.06
     overcrow
    0.06
    Act Density 0.000%

    No Known Activations