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

    Neuronpedia

    INDEX
    Explanations

    repeats, incomplete words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -suite
    -0.08
    رؤ
    -0.08
    commands
    -0.07
    gps
    -0.07
    ,N
    -0.07
    ่าง
    -0.07
    ,v
    -0.07
    precision
    -0.07
     nous
    -0.07
    为我们
    -0.07
    POSITIVE LOGITS
    蒋介石
    0.08
    𒀸
    0.07
    ի
    0.07
    .Monad
    0.07
    .viewmodel
    0.07
     originated
    0.07
     haunting
    0.07
    בור
    0.07
    삽
    0.07
    	ADD
    0.07
    Act Density 0.005%

    No Known Activations