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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кор
    -0.07
    𬜬
    -0.07
    スタート
    -0.07
    _PKT
    -0.07
    ケット
    -0.07
    🛫
    -0.07
    (Server
    -0.06
     Part
    -0.06
     :"
    -0.06
    LineNumber
    -0.06
    POSITIVE LOGITS
     thin
    0.08
    elim
    0.07
    美妙
    0.07
     の
    0.07
     hộ
    0.07
    (valid
    0.07
    	V
    0.07
    ultiple
    0.06
     live
    0.06
    ⊗
    0.06
    Act Density 0.012%

    No Known Activations