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

    Neuronpedia

    INDEX
    Explanations

    is **Key** or **best**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.32
     with
    0.30
    *
    0.28
    \
    0.27
    '
    0.26
    ?
    0.26
    [
    0.26
    ",
    0.26
    ();
    0.26
    with
    0.25
    POSITIVE LOGITS
     soooo
    0.27
     намного
    0.26
     horribly
    0.26
    怎樣
    0.24
     sooo
    0.24
     ridiculous
    0.24
     untenable
    0.24
     really
    0.24
    स्मै
    0.24
     hurting
    0.23
    Act Density 0.671%

    No Known Activations