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

    Neuronpedia

    INDEX
    Explanations

    say "day"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rible
    -0.07
     Х
    -0.07
    unic
    -0.07
    раст
    -0.06
     recounts
    -0.06
    西部
    -0.06
    roz
    -0.06
    ause
    -0.06
     microbes
    -0.06
    (play
    -0.06
    POSITIVE LOGITS
    日子
    0.08
     '+'
    0.07
    cap
    0.07
     mdb
    0.07
    ㉨
    0.07
     הציב
    0.07
     предоставлен
    0.07
    .currentUser
    0.07
    主動
    0.07
    laşma
    0.07
    Act Density 0.012%

    No Known Activations