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

    Neuronpedia

    INDEX
    Explanations

    llama

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     budding
    -0.09
    uchs
    -0.08
    autiful
    -0.07
     audit
    -0.07
     Parkinson
    -0.07
     btc
    -0.07
    ✈
    -0.07
     impecc
    -0.07
    yps
    -0.07
     mol
    -0.07
    POSITIVE LOGITS
    쩻
    0.08
    耿
    0.08
     rapp
    0.07
    _annotation
    0.07
     cassette
    0.07
    一台
    0.07
    Добав
    0.07
    黑
    0.07
     Blank
    0.07
    剩下的
    0.07
    Act Density 0.003%

    No Known Activations