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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     radians
    -0.06
    -backed
    -0.06
    公告
    -0.06
    	filter
    -0.06
     freq
    -0.05
     sandals
    -0.05
    лим
    -0.05
    ुक
    -0.05
    
    -0.05
     pří
    -0.05
    POSITIVE LOGITS
    apas
    0.07
     CSR
    0.07
     MainWindow
    0.07
    onsense
    0.06
     Napoli
    0.06
    ACY
    0.06
     temps
    0.06
    MODEL
    0.06
    èo
    0.06
     Tokyo
    0.06
    Act Density 0.004%

    No Known Activations