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

    Neuronpedia

    INDEX
    Explanations

    say "his"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    双方
    -0.09
     fé
    -0.09
     großen
    -0.08
     large
    -0.08
     Bộ
    -0.08
     parties
    -0.08
    ebox
    -0.08
     συμμε
    -0.08
     bộ
    -0.08
     sides
    -0.07
    POSITIVE LOGITS
    Placement
    0.10
     Placement
    0.10
     especializada
    0.09
     placement
    0.09
    Placed
    0.09
     estrateg
    0.09
     detener
    0.08
     geplaatst
    0.08
    	insert
    0.08
     preventiva
    0.08
    Act Density 0.001%

    No Known Activations