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

    Neuronpedia

    INDEX
    Explanations

    code related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fet
    -0.06
    aram
    -0.06
     капіт
    -0.06
    arshal
    -0.06
    _inner
    -0.06
    成本
    -0.06
    ，不过
    -0.06
    strap
    -0.06
    hdl
    -0.06
    busters
    -0.06
    POSITIVE LOGITS
     petty
    0.07
    .Alignment
    0.07
     lingu
    0.06
     pci
    0.06
     Chúa
    0.06
    ै,
    0.06
     Elm
    0.06
    .Translate
    0.06
    Ale
    0.06
    det
    0.06
    Act Density 0.000%

    No Known Activations