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

    Neuronpedia

    INDEX
    Explanations

    hashtags after topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -,
    0.54
    0.50
    .-\
    0.49
     -.
    0.45
    °-
    0.43
    0.43
    .;
    0.42
    }$;
    0.42
    --");
    0.42
     Critic
    0.42
    POSITIVE LOGITS
     #
    0.89
     hashtag
    0.80
     #[
    0.70
     hashtags
    0.66
     @
    0.61
    𓃵
    0.56
    /#
    0.54
     @_
    0.54
     pic
    0.54
     #(
    0.54
    Act Density 0.016%

    No Known Activations