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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Tree
    -0.07
    ตรง
    -0.07
     knife
    -0.06
     Kag
    -0.06
     Maher
    -0.06
     HLS
    -0.06
    layın
    -0.06
    r
    -0.06
    .btnCancel
    -0.06
     JIT
    -0.06
    POSITIVE LOGITS
    状况
    0.07
     compuls
    0.06
     nos
    0.06
     Handy
    0.06
     ):↵↵
    0.06
    ]))↵↵
    0.06
     Surg
    0.06
    (lua
    0.06
    Howard
    0.06
     );↵↵
    0.06
    Act Density 0.003%

    No Known Activations