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

    Neuronpedia

    INDEX
    Explanations

    turning on/off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    050
    -0.08
     manager
    -0.07
     awkward
    -0.06
     pallet
    -0.06
     Webb
    -0.06
    飯
    -0.06
     tissues
    -0.06
     man
    -0.06
    ничес
    -0.06
     households
    -0.06
    POSITIVE LOGITS
    τωση
    0.07
    ฯ
    0.07
    yük
    0.07
     wz
    0.07
     $($
    0.06
    ạy
    0.06
    >}↵
    0.06
    clide
    0.06
    езультат
    0.06
     ✔
    0.06
    Act Density 0.026%

    No Known Activations