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

    Neuronpedia

    INDEX
    Explanations

    wave behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    2.19
    𝙚
    2.05
    তিক্রম
    2.02
    これ
    2.00
    ted
    1.91
    ことができる
    1.89
    𝙧
    1.84
    >${
    1.81
    )">
    1.78
    >$
    1.78
    POSITIVE LOGITS
    wave
    2.32
    м
    2.26
     wave
    2.24
    illä
    2.23
    瀾
    1.99
     Socialista
    1.87
     waves
    1.86
    ired
    1.86
     tide
    1.85
     Wave
    1.83
    Act Density 0.021%

    No Known Activations