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

    Neuronpedia

    INDEX
    Explanations

    fun activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。,
    2.00
    된
    1.67
    ле
    1.63
    。
    1.62
    一定的
    1.56
     armor
    1.55
    ，
    1.55
    не
    1.53
     capitalize
    1.42
    一是
    1.42
    POSITIVE LOGITS
    ingly
    1.67
    ারি
    1.64
    nier
    1.64
    äk
    1.52
    ziele
    1.46
    Ako
    1.44
    ot
    1.43
    াৰ
    1.43
    Clik
    1.37
    पूर्वक
    1.36
    Act Density 0.172%

    No Known Activations