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

    Neuronpedia

    INDEX
    Explanations

    model response prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     игровые
    0.45
     eup
    0.40
     निजामाच्या
    0.39
    <unused1012>
    0.39
    lyPlugin
    0.39
     исключением
    0.39
    𒃶
    0.39
    𝙘
    0.39
    ър
    0.39
    пси
    0.38
    POSITIVE LOGITS
     it
    0.39
    Compared
    0.39
    0.37
     Wikipedia
    0.35
     When
    0.33
     Does
    0.33
     Compared
    0.32
     specifics
    0.32
     Riding
    0.32
     So
    0.31
    Act Density 0.089%

    No Known Activations