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

    Neuronpedia

    INDEX
    Explanations

    ceph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    代表性
    -0.07
    *.
    -0.07
    naz
    -0.07
    素质教育
    -0.07
    made
    -0.07
    elsing
    -0.07
    оз
    -0.06
     DISP
    -0.06
    סי
    -0.06
    ского
    -0.06
    POSITIVE LOGITS
    喻
    0.07
     eb
    0.07
     controller
    0.07
     Priest
    0.07
    _File
    0.07
     INTEGER
    0.07
     elseif
    0.07
    _Grid
    0.07
    呃
    0.06
    _ENT
    0.06
    Act Density 0.188%

    No Known Activations