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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToF
    -0.07
    	while
    -0.07
     OFF
    -0.06
     trophy
    -0.06
    ockets
    -0.06
     texts
    -0.06
    tube
    -0.06
     tok
    -0.06
    ERROR
    -0.06
    sock
    -0.06
    POSITIVE LOGITS
     │
    0.07
     angl
    0.07
    .ndarray
    0.07
     sal
    0.07
     başlam
    0.07
    \\\\
    0.07
     Investig
    0.06
     bộ
    0.06
    .baidu
    0.06
     aria
    0.06
    Act Density 0.066%

    No Known Activations