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

    Neuronpedia

    INDEX
    Explanations

    remainder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jour
    -0.09
     أكبر
    -0.08
    -button
    -0.08
     stagger
    -0.08
     plural
    -0.08
     Kard
    -0.07
     venir
    -0.07
     greenery
    -0.07
     Mila
    -0.07
     NATO
    -0.07
    POSITIVE LOGITS
     राशि
    0.08
     incertid
    0.08
     Суд
    0.08
    Unhandled
    0.08
     Eat
    0.07
     Scholars
    0.07
    ución
    0.07
    Extraction
    0.07
     polynomial
    0.07
     Extraction
    0.07
    Act Density 0.008%

    No Known Activations