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

    Neuronpedia

    INDEX
    Explanations

    y=x equation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     조사
    -0.09
     Investig
    -0.09
     التهاب
    -0.09
     Investigation
    -0.08
     기사
    -0.08
     Ing
    -0.08
     Advertisement
    -0.08
     inflammation
    -0.08
     Sponsored
    -0.08
    inations
    -0.07
    POSITIVE LOGITS
     diagonal
    0.11
    Diagonal
    0.11
     diag
    0.09
    diag
    0.09
    स्व
    0.09
     बराब
    0.09
    identity
    0.09
     swaps
    0.09
     espejo
    0.08
     equil
    0.08
    Act Density 0.033%

    No Known Activations