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

    Neuronpedia

    INDEX
    Explanations

    introductions and section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮃ
    0.49
    ﻥ
    0.49
     шрифт
    0.48
    that
    0.45
    ادي
    0.45
     той
    0.44
     бала
    0.43
    диви
    0.43
    ിലോ
    0.43
    டி
    0.43
    POSITIVE LOGITS
     ep
    0.60
     represents
    0.54
     Ep
    0.50
     predecessors
    0.50
    ye
    0.49
     cherry
    0.48
     representatives
    0.46
     orchids
    0.46
     represent
    0.46
    y
    0.46
    Act Density 0.001%

    No Known Activations