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

    Neuronpedia

    INDEX
    Explanations

    listing connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pentru
    0.64
     pentru
    0.57
     で
    0.57
     takže
    0.55
    Pentru
    0.54
     είναι
    0.54
     Analyse
    0.54
     Untuk
    0.54
     例如
    0.52
     について
    0.51
    POSITIVE LOGITS
     and
    1.90
     or
    1.88
     или
    1.88
    และ
    1.85
     ও
    1.79
     மற்றும்
    1.75
    หรือ
    1.74
     বা
    1.73
     અને
    1.70
    或
    1.70
    Act Density 0.521%

    No Known Activations