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

    Neuronpedia

    INDEX
    Explanations

    by, or, in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     O
    0.40
    わざ
    0.39
     OCPP
    0.38
    びっくり
    0.38
     Saying
    0.38
    銥
    0.38
    รก
    0.38
     shocked
    0.38
    anese
    0.37
    ಯು
    0.37
    POSITIVE LOGITS
     movingRect
    0.49
    idler
    0.45
    encoder
    0.43
    algorithms
    0.42
    spoken
    0.42
    pointer
    0.41
    satisf
    0.40
     पोर्ट
    0.40
    port
    0.40
    controller
    0.40
    Act Density 0.000%

    No Known Activations