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

    Neuronpedia

    INDEX
    Explanations

    Math theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _renderer
    -0.09
    (renderer
    -0.09
    ವಿ
    -0.08
     Ravi
    -0.08
    mooth
    -0.08
     cannabinoids
    -0.08
    пони
    -0.08
    .interpolate
    -0.08
     pitches
    -0.08
    Metal
    -0.08
    POSITIVE LOGITS
     Maxim
    0.10
     maximizing
    0.09
     Erd
    0.09
     maximize
    0.09
     quota
    0.09
     magyar
    0.09
     Sper
    0.09
     maximise
    0.08
     cardinal
    0.08
     Aktivitäten
    0.08
    Act Density 0.016%

    No Known Activations