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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _traj
    -0.07
    deg
    -0.07
    .setProperty
    -0.06
    /ph
    -0.06
    efficient
    -0.06
    .',
↵
    -0.06
     functions
    -0.06
    为此
    -0.06
     leadership
    -0.06
    公司的
    -0.06
    POSITIVE LOGITS
     alışver
    0.07
     Starter
    0.07
     בחיים
    0.07
    ń
    0.07
    诰
    0.06
    考虑
    0.06
     işlet
    0.06
     kaldır
    0.06
    🤨
    0.06
    ambda
    0.06
    Act Density 0.048%

    No Known Activations