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

    Neuronpedia

    INDEX
    Explanations

    a the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    াঁ
    -0.09
     MUL
    -0.08
    PWD
    -0.08
    PIX
    -0.08
     SO
    -0.08
     insults
    -0.08
     VV
    -0.08
    _certificate
    -0.07
     ART
    -0.07
    Certificate
    -0.07
    POSITIVE LOGITS
     maximizing
    0.12
     maximize
    0.11
     optimizing
    0.11
     optimum
    0.10
     optimization
    0.09
     maximise
    0.09
    Optimize
    0.09
     optimize
    0.09
    iest
    0.09
     allocate
    0.08
    Act Density 0.027%

    No Known Activations