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

    Neuronpedia

    INDEX
    Explanations

    people involved or affected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انه
    0.72
     desarrollado
    0.71
     obligatorio
    0.71
     lequel
    0.68
    سيط
    0.67
     amelyet
    0.67
     accompagné
    0.67
     vedno
    0.67
     limitado
    0.67
     শিষ
    0.67
    POSITIVE LOGITS
     involved
    1.59
     affected
    1.40
     impacted
    1.19
    involved
    1.04
     Involved
    1.03
    affected
    1.01
     caught
    1.00
     Affected
    0.97
     participating
    0.96
     receiving
    0.89
    Act Density 0.150%

    No Known Activations