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

    Neuronpedia

    INDEX
    Explanations

    250 and 350

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     开
    -0.07
    켜
    -0.06
     Makeup
    -0.06
    Ü
    -0.06
    _routing
    -0.06
     開
    -0.06
    	settings
    -0.06
     establishment
    -0.06
    NotNull
    -0.06
     Heating
    -0.06
    POSITIVE LOGITS
    250
    0.08
    351
    0.08
    751
    0.08
    750
    0.08
    150
    0.08
                    
    0.07
    650
    0.07
     Robinson
    0.07
     Jones
    0.07
    850
    0.07
    Act Density 0.120%

    No Known Activations