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

    Neuronpedia

    INDEX
    Explanations

    counting three items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    თვის
    2.27
    на
    2.25
    ش
    2.20
    sz
    2.17
    ্লাহ
    2.05
    서
    2.05
    𝗶
    2.02
    폿
    2.02
    st
    1.98
    ta
    1.98
    POSITIVE LOGITS
    ϲ
    2.16
    P
    1.95
    T
    1.92
    fifths
    1.88
    R
    1.77
    RING
    1.72
     ascertaining
    1.66
    째
    1.64
    ѕ
    1.64
    Ι
    1.63
    Act Density 0.289%

    No Known Activations