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

    Neuronpedia

    INDEX
    Explanations

    evening time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ランク
    0.69
    izable
    0.66
    Delete
    0.65
    plaintext
    0.65
    これも
    0.64
    보기
    0.64
    immutable
    0.63
    长期
    0.63
    Instant
    0.63
    គ្ន
    0.63
    POSITIVE LOGITS
     onwards
    1.64
     onward
    1.28
     sharp
    1.26
    sharp
    1.11
     Sharp
    1.11
     departure
    1.02
     ish
    1.02
     Departure
    0.95
    Sharp
    0.94
     સુધી
    0.89
    Act Density 0.047%

    No Known Activations