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

    Neuronpedia

    INDEX
    Explanations

    unes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sd
    -0.07
     resp
    -0.07
     Вас
    -0.07
     δυ
    -0.06
    ahlen
    -0.06
    .cod
    -0.06
     ela
    -0.06
     图
    -0.06
    tank
    -0.06
    .access
    -0.06
    POSITIVE LOGITS
    .friend
    0.07
    زی
    0.07
     demolition
    0.06
     deposition
    0.06
    accumulate
    0.06
    (sess
    0.06
     graceful
    0.06
     ({↵
    0.06
    _destination
    0.06
    qv
    0.06
    Act Density 0.000%

    No Known Activations