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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในร
    -0.07
    ľ
    -0.06
     близ
    -0.06
     evidently
    -0.06
     dre
    -0.06
     вс
    -0.06
    拔
    -0.06
    _BACKEND
    -0.06
     چیزی
    -0.06
     Miss
    -0.06
    POSITIVE LOGITS
     bisher
    0.07
    .InteropServices
    0.07
     Xm
    0.07
    .mixer
    0.06
    ریک
    0.06
    edii
    0.06
     적용
    0.06
    .]
    0.06
    (ci
    0.06
    (norm
    0.06
    Act Density 0.022%

    No Known Activations