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

    Neuronpedia

    INDEX
    Explanations

    IR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	my
    -0.06
    fdb
    -0.06
     �
    -0.06
     filled
    -0.06
    ’all
    -0.06
    .used
    -0.06
     coment
    -0.05
     depicts
    -0.05
    偏
    -0.05
    金融
    -0.05
    POSITIVE LOGITS
     cerr
    0.07
    ılmıştır
    0.07
     Statue
    0.07
    หลวง
    0.07
     zengin
    0.06
     doprav
    0.06
     Ther
    0.06
     [{↵
    0.06
    liqu
    0.06
     corr
    0.06
    Act Density 0.002%

    No Known Activations