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

    Neuronpedia

    INDEX
    Explanations

    multiplication and addition steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.99
    ਾਂ
    0.98
     frente
    0.98
    बर
    0.97
     moż
    0.96
     الجه
    0.96
     chorizo
    0.95
     ANAL
    0.95
     richtigen
    0.95
    ਾ
    0.94
    POSITIVE LOGITS
    TextureData
    0.97
     Apesar
    0.94
     transmiss
    0.92
     propelling
    0.91
     atualmente
    0.90
    otipos
    0.90
     transplanted
    0.90
     tecido
    0.90
     exacerbated
    0.89
    coated
    0.88
    Act Density 0.002%

    No Known Activations