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

    Neuronpedia

    INDEX
    Explanations

    computer files and documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PIN
    -0.06
    위를
    -0.06
     dz
    -0.06
    drag
    -0.06
     splits
    -0.06
    Pr
    -0.06
     polis
    -0.06
    ِن
    -0.06
    路
    -0.06
    _pic
    -0.06
    POSITIVE LOGITS
    	center
    0.07
     circ
    0.07
     Fach
    0.06
    _RESERVED
    0.06
    溶
    0.06
    .sem
    0.06
     Dess
    0.06
    .Admin
    0.06
    删除
    0.06
     brill
    0.06
    Act Density 0.001%

    No Known Activations