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

    Neuronpedia

    INDEX
    Explanations

    shades of yellow and pink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     साउथ
    0.46
    utors
    0.46
    sächlich
    0.45
    apses
    0.44
    ivores
    0.44
    væ
    0.44
    odym
    0.44
    calright
    0.44
    employer
    0.43
     salari
    0.43
    POSITIVE LOGITS
     thorough
    0.50
    یشه
    0.48
     termin
    0.45
     Troubles
    0.45
     큰
    0.44
    ния
    0.44
     code
    0.44
     easily
    0.44
     chen
    0.43
     Thorough
    0.43
    Act Density 0.005%

    No Known Activations