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

    Neuronpedia

    INDEX
    Explanations

    media descriptions and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fläche
    0.77
    ubehör
    0.73
    ETERS
    0.70
    issors
    0.70
    osomes
    0.70
    блица
    0.66
    redients
    0.66
    localhost
    0.65
     clauses
    0.65
    icing
    0.65
    POSITIVE LOGITS
     masterpiece
    1.73
     thriller
    1.72
     dystopian
    1.56
     satirical
    1.55
     blockbuster
    1.45
     novels
    1.45
     documentary
    1.44
     acclaimed
    1.39
     documentaries
    1.38
     steampunk
    1.35
    Act Density 0.318%

    No Known Activations