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
     לאורך
    -0.08
    دت
    -0.07
    ront
    -0.07
     Working
    -0.07
     looked
    -0.07
     nó
    -0.07
    Work
    -0.07
     fois
    -0.06
     Era
    -0.06
     rushing
    -0.06
    POSITIVE LOGITS
    _Enc
    0.07
     Dest
    0.07
    升值
    0.07
     Investor
    0.06
    储
    0.06
    _vert
    0.06
    今日头条
    0.06
    пт
    0.06
    _flat
    0.06
    谐
    0.06
    Act Density 0.075%

    No Known Activations