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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Screens
    -0.08
     forgotten
    -0.08
    .Pass
    -0.08
    ambiguous
    -0.08
    Routes
    -0.07
     interactions
    -0.07
     radicals
    -0.07
    Signed
    -0.06
    Acc
    -0.06
     sending
    -0.06
    POSITIVE LOGITS
     الول
    0.07
    =("
    0.06
     anlamda
    0.06
     méth
    0.06
     která
    0.06
     boyut
    0.06
     açısından
    0.06
     ži
    0.06
     одна
    0.06
     نوع
    0.06
    Act Density 0.026%

    No Known Activations