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

    Neuronpedia

    INDEX
    Explanations

    Know Your Meme or help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jour
    0.40
     அம
    0.38
    ritos
    0.38
    મુ
    0.37
     subdued
    0.37
     couture
    0.37
     finest
    0.36
     sloping
    0.36
    த்து
    0.36
    mediated
    0.36
    POSITIVE LOGITS
    !">
    0.68
    !:
    0.68
    !",
    0.64
    !',
    0.63
    !,
    0.62
    !-
    0.62
    !”,
    0.61
    !”.
    0.59
    !(
    0.58
    !“
    0.57
    Act Density 0.037%

    No Known Activations