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

    Neuronpedia

    INDEX
    Explanations

    -Identifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    服務
    -0.06
     named
    -0.06
     miss
    -0.06
     notch
    -0.06
    Officers
    -0.06
     warrant
    -0.06
    𝓿
    -0.06
     volver
    -0.06
    _uuid
    -0.06
     suck
    -0.06
    POSITIVE LOGITS
    国防
    0.08
    angepicker
    0.07
    _corpus
    0.07
     shortly
    0.07
    京
    0.07
    精通
    0.07
     McGregor
    0.07
    secondary
    0.07
    				↵
    0.07
     Passenger
    0.07
    Act Density 0.004%

    No Known Activations