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

    Neuronpedia

    INDEX
    Explanations

    preparing for recursive processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Forest
    0.55
     Dumb
    0.46
    lar
    0.46
     Friendship
    0.45
    Forest
    0.44
     Conquest
    0.44
     forest
    0.43
     Sah
    0.43
     Smithsonian
    0.43
     Wheeler
    0.43
    POSITIVE LOGITS
     ذریع
    0.51
    𝒋
    0.50
    tidak
    0.49
     مراکز
    0.46
    ラクマ
    0.46
    ukuoka
    0.46
    犇
    0.46
    𝘫
    0.46
     abaste
    0.46
    perplexity
    0.45
    Act Density 0.005%

    No Known Activations