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

    Neuronpedia

    INDEX
    Explanations

    GCD calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aw
    -0.08
    olding
    -0.07
     मात
    -0.07
     avoiding
    -0.07
    iting
    -0.07
     Containers
    -0.06
     januari
    -0.06
    page
    -0.06
     containers
    -0.06
     mik
    -0.06
    POSITIVE LOGITS
     samedi
    0.08
     plano
    0.08
     diminution
    0.08
    -Claude
    0.08
    Plano
    0.08
    gare
    0.08
     farinha
    0.08
     Plano
    0.08
     plafond
    0.08
     cramps
    0.08
    Act Density 0.361%

    No Known Activations