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

    Neuronpedia

    INDEX
    Explanations

    graphing numbers yield

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uncertain
    0.58
    set
    0.52
    name
    0.49
    button
    0.46
    marital
    0.46
    usual
    0.46
    ire
    0.46
    height
    0.45
    worth
    0.44
    family
    0.44
    POSITIVE LOGITS
     solcher
    0.49
     фильм
    0.47
     dessas
    0.46
     філь
    0.45
     фильма
    0.44
    على
    0.43
     ван
    0.43
     eels
    0.43
     миллиар
    0.43
     як
    0.42
    Act Density 0.002%

    No Known Activations