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

    Neuronpedia

    INDEX
    Explanations

    chess board squares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assemblies
    -0.09
     берем
    -0.08
     offer
    -0.08
     Infragistics
    -0.08
     Jimmy
    -0.07
     Beach
    -0.07
     Ipsum
    -0.07
    ಿದು
    -0.07
     stimuli
    -0.07
     Larry
    -0.07
    POSITIVE LOGITS
     diagon
    0.11
     bishop
    0.10
     protegido
    0.09
     bishops
    0.08
     diagonal
    0.08
     Knights
    0.08
    ဒ
    0.08
    Diagonal
    0.08
     knight
    0.08
     couleur
    0.08
    Act Density 0.004%

    No Known Activations