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

    Neuronpedia

    INDEX
    Explanations

    interventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ludwig
    -0.07
    dü
    -0.06
     provider
    -0.06
    Child
    -0.06
    这些
    -0.06
    celand
    -0.06
     Після
    -0.06
     octave
    -0.06
     sharper
    -0.06
     leng
    -0.06
    POSITIVE LOGITS
     mechanism
    0.07
    	namespace
    0.06
    .yy
    0.06
    鲁
    0.06
    �
    0.06
     bat
    0.06
    -three
    0.06
    难
    0.06
     audible
    0.06
    .coroutines
    0.06
    Act Density 0.159%

    No Known Activations