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

    Neuronpedia

    INDEX
    Explanations

    accepted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ar
    -0.07
     본
    -0.07
    _Invoke
    -0.06
     groundwork
    -0.06
    remain
    -0.06
    Bearer
    -0.06
     boh
    -0.06
    _exact
    -0.06
    เล
    -0.06
    .getZ
    -0.06
    POSITIVE LOGITS
    ismatch
    0.07
    luluk
    0.06
    िश
    0.06
     Ibrahim
    0.06
     tedbir
    0.06
    -param
    0.06
     activeClassName
    0.06
    �
    0.06
    757
    0.06
    เทศ
    0.06
    Act Density 0.020%

    No Known Activations