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

    Neuronpedia

    INDEX
    Explanations

    goals and objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.48
    $'
    0.48
     the
    0.47
    $,
    0.47
    3
    0.46
    road
    0.45
    RO
    0.45
    ro
    0.44
    %,
    0.44
    $$
    0.43
    POSITIVE LOGITS
    中华
    0.49
    uları
    0.49
    𒊹
    0.46
    ಥ
    0.45
     pouquinho
    0.45
     والمر
    0.44
    ußen
    0.44
    جميع
    0.43
    ッフ
    0.43
     Irlanda
    0.43
    Act Density 0.000%

    No Known Activations