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

    Neuronpedia

    INDEX
    Explanations

    mental calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gated
    -0.08
    viol
    -0.08
     GDPR
    -0.08
    Compliance
    -0.08
     Laval
    -0.07
    .vert
    -0.07
    Ether
    -0.07
    Ε
    -0.07
     valign
    -0.07
     esem
    -0.07
    POSITIVE LOGITS
     approximate
    0.10
     уме
    0.10
    最快
    0.10
     aproxima
    0.09
     воспольз
    0.09
     astuces
    0.09
     aproxim
    0.09
     الكس
    0.09
    _digits
    0.09
     دستی
    0.09
    Act Density 0.030%

    No Known Activations