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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Davies
    -0.07
    Longitude
    -0.06
     女
    -0.06
     '*
    -0.06
    Version
    -0.06
     변
    -0.06
    лением
    -0.06
     ordained
    -0.06
    ess
    -0.06
    	status
    -0.06
    POSITIVE LOGITS
    askan
    0.06
    >NN
    0.06
    ......
    0.06
    html
    0.06
    IRD
    0.06
     بالن
    0.06
     doi
    0.06
    �
    0.06
    ManagedObject
    0.06
    ORIZED
    0.06
    Act Density 0.021%

    No Known Activations