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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     말
    -0.07
     아침
    -0.06
     plethora
    -0.06
     Wol
    -0.06
    ет
    -0.06
     пару
    -0.06
    	M
    -0.06
    (keys
    -0.06
    xe
    -0.06
    Adam
    -0.06
    POSITIVE LOGITS
     Highlight
    0.07
     calendar
    0.07
    UY
    0.06
     vibr
    0.06
    (Component
    0.06
     Ball
    0.06
    いた
    0.06
     primary
    0.06
    ανα
    0.06
    .Player
    0.06
    Act Density 0.000%

    No Known Activations