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

    Neuronpedia

    INDEX
    Explanations

    harmonics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्तार
    0.57
     doute
    0.54
    ),]),
    0.54
    اران
    0.53
    дку
    0.52
     UIS
    0.51
     tino
    0.51
     koj
    0.50
    ље
    0.50
     anecd
    0.50
    POSITIVE LOGITS
    ine
    0.58
     B
    0.54
    z
    0.53
    uk
    0.52
    pathy
    0.51
    b
    0.51
    en
    0.50
    cal
    0.49
    pet
    0.48
    sel
    0.48
    Act Density 0.000%

    No Known Activations