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

    Neuronpedia

    INDEX
    Explanations

    without revealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ves
    0.44
    sequence
    0.44
    boy
    0.44
    vigor
    0.42
    comb
    0.42
    begin
    0.42
    biod
    0.42
    s
    0.41
    Future
    0.41
    ctic
    0.41
    POSITIVE LOGITS
    ሉ።
    0.51
    .?
    0.49
    тала
    0.47
    .*/
    0.46
    ității
    0.46
    м
    0.45
     dumpfile
    0.45
    ؟.
    0.44
    Л
    0.43
    0.43
    Act Density 0.003%

    No Known Activations