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

    Neuronpedia

    INDEX
    Explanations

    beginning or parent cell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    А
    0.98
    Бе
    0.93
    К
    0.90
    лів
    0.89
    Ба
    0.88
    де
    0.84
     listView
    0.84
     Clin
    0.83
    ttes
    0.82
    Э
    0.82
    POSITIVE LOGITS
    uous
    1.09
    um
    1.07
    ur
    1.04
     vliegt
    1.00
    antation
    0.98
    ৩৮
    0.96
     всего
    0.94
    ৩৭
    0.93
    _
    0.93
     verbunden
    0.91
    Act Density 0.161%

    No Known Activations