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

    Neuronpedia

    INDEX
    Explanations

    CSS sizing and box model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    by
    0.39
    rem
    0.38
    __
    0.38
    --
    0.38
    .--
    0.37
     Calder
    0.37
    imeo
    0.35
    ├──
    0.35
    iles
    0.34
    ty
    0.34
    POSITIVE LOGITS
     textbox
    0.43
     Doodle
    0.42
    dets
    0.40
    噺
    0.38
     ресу
    0.37
     دھ
    0.37
     πίνακα
    0.37
    ँचा
    0.37
     вокруг
    0.36
     보면은
    0.36
    Act Density 0.014%

    No Known Activations