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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     유형
    -0.07
     patt
    -0.06
    करण
    -0.06
    自身
    -0.06
     zůst
    -0.06
     afirm
    -0.06
     모집
    -0.06
    _stamp
    -0.06
    	day
    -0.06
     Nẵng
    -0.06
    POSITIVE LOGITS
     freeze
    0.07
    イツ
    0.07
    加入
    0.07
     reversal
    0.06
     '')↵
    0.06
    allocated
    0.06
    Finance
    0.06
     customs
    0.06
     procure
    0.06
     Catholic
    0.06
    Act Density 0.003%

    No Known Activations