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

    Neuronpedia

    INDEX
    Explanations

    smart assistant or integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ř
    0.49
    ẓ
    0.46
     unavoid
    0.46
    şik
    0.45
    õ
    0.45
    😣
    0.45
    ķ
    0.45
    ⚭
    0.45
    er
    0.44
    神奇
    0.44
    POSITIVE LOGITS
     I
    0.56
     yield
    0.49
     Imagen
    0.47
     quede
    0.47
     topology
    0.44
     him
    0.43
    ным
    0.43
     agendas
    0.43
     dine
    0.42
     ART
    0.42
    Act Density 0.000%

    No Known Activations