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

    Neuronpedia

    INDEX
    Explanations

    by followed by method or agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.29
    ↵↵
    0.25
    né
    0.23
     can
    0.23
    म
    0.23
    ר
    0.23
    ാ
    0.23
    м
    0.22
    ්‍
    0.22
    ם
    0.22
    POSITIVE LOGITS
     virtue
    0.50
     dint
    0.40
    zantine
    0.33
     means
    0.29
    products
    0.27
     nécessité
    0.26
     rote
    0.26
     separado
    0.26
     inserting
    0.26
     mistake
    0.25
    Act Density 0.100%

    No Known Activations