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

    Neuronpedia

    INDEX
    Explanations

    before playing, watching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fudai
    0.48
     تعالی
    0.46
    піль
    0.44
    ℡
    0.44
     uczni
    0.43
     dritte
    0.43
     TMN
    0.43
    бек
    0.43
     pamię
    0.43
     hton
    0.43
    POSITIVE LOGITS
    ka
    0.44
    anol
    0.39
    ים
    0.39
    getStartState
    0.38
    ant
    0.38
    icale
    0.37
    க்களை
    0.37
    s
    0.37
    ot
    0.36
     কা
    0.36
    Act Density 0.001%

    No Known Activations