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

    Neuronpedia

    INDEX
    Explanations

    util

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    北路
    -0.07
    elper
    -0.07
    нт
    -0.07
    起重
    -0.07
    계획
    -0.06
    промышленн
    -0.06
    摇头
    -0.06
    Violation
    -0.06
     Historical
    -0.06
     Infer
    -0.06
    POSITIVE LOGITS
    .]↵↵
    0.07
    ).↵↵
    0.07
    >")↵
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     profit
    0.06
    ([]);↵
    0.06
    "){
↵
    0.06
    channel
    0.06
    _NUMBER
    0.06
     settled
    0.06
    Act Density 0.001%

    No Known Activations