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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    普通人
    -0.07
    _Offset
    -0.07
    摔倒
    -0.07
    Bitcoin
    -0.07
     ``(
    -0.07
    ILED
    -0.07
    צילום
    -0.07
     anlaşma
    -0.07
    	WHERE
    -0.07
    bij
    -0.07
    POSITIVE LOGITS
     ak
    0.07
    $date
    0.06
    牮
    0.06
    ////////////////
    0.06
     prepare
    0.06
    类
    0.06
    ằ
    0.06
    /game
    0.06
    骅
    0.06
     detach
    0.06
    Act Density 0.005%

    No Known Activations