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

    Neuronpedia

    INDEX
    Explanations

    bringing the war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mios
    0.90
     comprimento
    0.90
    booked
    0.86
     findet
    0.84
    ึ่ง
    0.84
     entspricht
    0.83
     کم
    0.83
    苳
    0.82
     rispett
    0.81
     필요
    0.79
    POSITIVE LOGITS
    Prote
    0.77
     Prote
    0.76
    a
    0.74
    es
    0.73
    पर
    0.69
     Cit
    0.69
    arsen
    0.68
    钤
    0.67
    AD
    0.67
    Tar
    0.67
    Act Density 0.001%

    No Known Activations