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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snyder
    -0.07
     permanent
    -0.07
     clergy
    -0.06
    局
    -0.06
     kèm
    -0.06
    以来
    -0.06
    StateManager
    -0.06
     gly
    -0.06
     subsystem
    -0.06
    ثير
    -0.06
    POSITIVE LOGITS
     illumin
    0.07
    product
    0.07
    	action
    0.06
    مال
    0.06
    .office
    0.06
    โ
    0.06
     Не
    0.06
     EVE
    0.06
     subscriptions
    0.06
    .criteria
    0.06
    Act Density 0.003%

    No Known Activations