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

    Neuronpedia

    INDEX
    Explanations

    punctuation/dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     선정
    -0.09
     recommandé
    -0.08
     colonne
    -0.08
     Reference
    -0.08
     catal
    -0.08
     توص
    -0.07
     curry
    -0.07
     buah
    -0.07
     RP
    -0.07
     રંગ
    -0.07
    POSITIVE LOGITS
     disclosures
    0.10
     autobi
    0.10
     dichiar
    0.09
    Disclosure
    0.09
     declaration
    0.09
     voluntarily
    0.09
     заявил
    0.09
    Declarations
    0.09
     autobiography
    0.09
     confess
    0.09
    Act Density 0.332%

    No Known Activations