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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    各種
    0.51
     various
    0.51
     Various
    0.48
    各种
    0.47
     vários
    0.47
    Various
    0.46
     numerous
    0.44
     several
    0.43
     etc
    0.43
     sebagainya
    0.43
    POSITIVE LOGITS
     penultimate
    0.52
    有两种
    0.42
    ⿸
    0.40
    株式会社
    0.37
    pubescens
    0.37
    有两个
    0.37
    ối
    0.36
    ManagerProxy
    0.35
    Lastly
    0.35
    ęcia
    0.34
    Act Density 0.068%

    No Known Activations