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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    κ
    0.51
    sweet
    0.49
    in
    0.45
    stars
    0.44
    t
    0.43
    i
    0.43
    is
    0.42
    sprecher
    0.42
    te
    0.42
    си
    0.42
    POSITIVE LOGITS
     translateY
    0.45
     predmet
    0.42
    Hopefully
    0.42
     rapporti
    0.39
    ہ
    0.38
    🏆
    0.38
    前往
    0.38
     malheureusement
    0.38
    AY
    0.38
    每年
    0.37
    Act Density 0.001%

    No Known Activations