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

    Neuronpedia

    INDEX
    Explanations

    Installation instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oug
    -0.08
    rosso
    -0.07
     barg
    -0.07
     Luke
    -0.06
    .herokuapp
    -0.06
    🐆
    -0.06
    .names
    -0.06
    GHz
    -0.06
    再来
    -0.06
    🎐
    -0.06
    POSITIVE LOGITS
    .detectChanges
    0.07
    "',
    0.07
     leadership
    0.07
    驿站
    0.07
    ᵞ
    0.07
    Sharper
    0.07
    研究院
    0.07
    늠
    0.07
    _maker
    0.06
    Ԍ
    0.06
    Act Density 0.035%

    No Known Activations