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

    Neuronpedia

    INDEX
    Explanations

    what is obtained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ’
    0.42
    ’
    0.40
    IB
    0.40
    ğu
    0.39
    agnie
    0.38
    verted
    0.38
    anga
    0.38
     regenerating
    0.37
    IS
    0.37
     ترمیم
    0.37
    POSITIVE LOGITS
     obtenido
    0.76
     obtenidos
    0.74
     Obtained
    0.70
     obtained
    0.68
     obtenus
    0.68
     obtenue
    0.61
     ottenuto
    0.60
     obtenu
    0.56
     otten
    0.55
     حاصل
    0.55
    Act Density 0.013%

    No Known Activations