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

    Neuronpedia

    INDEX
    Explanations

    drivetrain package, relatable situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synonym
    0.45
    钤
    0.44
     seyd
    0.43
     defended
    0.43
     hi
    0.42
     ἀ
    0.41
    mapKey
    0.40
     vai
    0.39
     означа
    0.39
     fong
    0.39
    POSITIVE LOGITS
    atihan
    0.45
     ایکسپریس
    0.42
    Fre
    0.41
    ological
    0.40
    endl
    0.40
     Sciences
    0.40
     SCIENCES
    0.39
    ontaneous
    0.39
    expenses
    0.38
    seem
    0.38
    Act Density 0.012%

    No Known Activations