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

    Neuronpedia

    INDEX
    Explanations

    don't followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ынша
    0.53
     fledgling
    0.49
     dodgy
    0.45
    jeeling
    0.44
    GoAbroad
    0.43
    пература
    0.43
     shavings
    0.42
    EqualTo
    0.42
     authored
    0.41
     Galactic
    0.41
    POSITIVE LOGITS
    '
    0.49
    and
    0.45
    älle
    0.45
    ogie
    0.45
    ß
    0.45
     de
    0.44
    _
    0.44
    alla
    0.43
    3
    0.41
    to
    0.41
    Act Density 0.004%

    No Known Activations