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

    Neuronpedia

    INDEX
    Explanations

    data structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alse
    1.11
    ſelf
    1.01
    assertTrue
    0.98
    als
    0.94
    riy
    0.92
     eig
    0.91
    ualitas
    0.89
    మ్ము
    0.89
    tract
    0.88
     glum
    0.88
    POSITIVE LOGITS
    このように
    1.01
    0.99
    ভাবেই
    0.94
    蛳
    0.94
     twists
    0.93
     എങ്ങനെ
    0.92
     специалист
    0.92
    0.92
    //@
    0.92
    Provide
    0.92
    Act Density 0.001%

    No Known Activations