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

    Neuronpedia

    INDEX
    Explanations

    positive reception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jails
    -0.07
    	string
    -0.06
    ön
    -0.06
     انقلاب
    -0.06
     ]}↵
    -0.06
    	BufferedReader
    -0.06
    =this
    -0.06
    etě
    -0.06
    距
    -0.06
    STYLE
    -0.06
    POSITIVE LOGITS
    가능
    0.08
    Contr
    0.07
     benefits
    0.06
     Enough
    0.06
    �
    0.06
     dáv
    0.06
    _Pre
    0.06
     Ther
    0.06
     benefit
    0.06
     accr
    0.06
    Act Density 0.074%

    No Known Activations