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

    Neuronpedia

    INDEX
    Explanations

    keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     单
    -0.07
     sow
    -0.07
    单
    -0.07
    單
    -0.07
    妖
    -0.06
     Wants
    -0.06
     delegated
    -0.06
    usiness
    -0.06
     Manson
    -0.06
     Doyle
    -0.06
    POSITIVE LOGITS
    šak
    0.07
    .LayoutControlItem
    0.06
     keys
    0.06
    	errors
    0.06
    솔
    0.06
     RH
    0.06
     Mastery
    0.06
    аж
    0.06
     reliable
    0.06
    chemy
    0.06
    Act Density 0.005%

    No Known Activations