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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worth
    -0.07
    [↵
    -0.07
     tuple
    -0.06
     soutě
    -0.06
     doGet
    -0.06
    천
    -0.06
    �
    -0.06
     sweets
    -0.06
    _mpi
    -0.06
     Laden
    -0.06
    POSITIVE LOGITS
    곳
    0.07
    ौं
    0.06
    _Set
    0.06
    	statement
    0.06
    TZ
    0.06
    awks
    0.06
    样子
    0.06
     hunter
    0.06
     себе
    0.06
    Endpoints
    0.06
    Act Density 0.170%

    No Known Activations