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

    Neuronpedia

    INDEX
    Explanations

    limitations/restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    提问
    -0.07
    stripe
    -0.07
    ענק
    -0.07
     wave
    -0.07
    ilit
    -0.07
    طرق
    -0.07
     streak
    -0.07
     Canadians
    -0.06
     cape
    -0.06
    back
    -0.06
    POSITIVE LOGITS
    .pivot
    0.07
     ''}↵
    0.07
    ᴓ
    0.07
     Ро
    0.07
    ѿ
    0.07
    iotic
    0.07
     Cinema
    0.07
    _REUSE
    0.06
    好奇
    0.06
    _A
    0.06
    Act Density 0.069%

    No Known Activations