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

    Neuronpedia

    INDEX
    Explanations

    objective and unbiased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kiego
    0.51
     decou
    0.50
     plugged
    0.49
     hinged
    0.48
     possessions
    0.48
     domestically
    0.48
     decision
    0.47
     hashed
    0.47
    াহিনী
    0.46
     downstairs
    0.46
    POSITIVE LOGITS
    润
    0.54
    (
    0.54
    ’
    0.52
    '
    0.47
    र
    0.47
     opus
    0.47
     Y
    0.47
    Ons
    0.47
    ´
    0.46
    爱
    0.46
    Act Density 0.001%

    No Known Activations