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

    Neuronpedia

    INDEX
    Explanations

    assessment for learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⬯
    0.55
    განიზ
    0.53
    嵃
    0.51
    喈
    0.49
     znač
    0.48
    দায়িক
    0.48
    द्दाख
    0.48
     ardından
    0.48
    SupportActionBar
    0.48
     visok
    0.48
    POSITIVE LOGITS
    ,
    0.46
    orems
    0.42
    atuan
    0.42
    !
    0.42
    \%
    0.42
    )(
    0.41
    )_{
    0.41
    ]_{
    0.40
    \%,
    0.40
    _{\
    0.40
    Act Density 0.000%

    No Known Activations