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

    Neuronpedia

    INDEX
    Explanations

    your best friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ˹
    0.41
    Ꮬ
    0.38
     slo
    0.36
     Practically
    0.36
    Totally
    0.35
    Putting
    0.35
    THIRD
    0.35
     hos
    0.34
     Staffel
    0.34
    eful
    0.34
    POSITIVE LOGITS
    茈
    0.40
    wissenschaft
    0.39
    alik
    0.38
    瑄
    0.38
     pivoted
    0.38
     విజయ
    0.37
    қу
    0.36
     поворо
    0.36
     Senior
    0.36
     reflecting
    0.36
    Act Density 0.024%

    No Known Activations