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

    Neuronpedia

    INDEX
    Explanations

    certainly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     developments
    -0.07
     lut
    -0.07
    ahas
    -0.07
    cision
    -0.06
    *math
    -0.06
     quarters
    -0.06
    异
    -0.06
     δη
    -0.06
    _STAR
    -0.06
    复
    -0.06
    POSITIVE LOGITS
    xiv
    0.07
     FStar
    0.06
     obe
    0.06
    .Tree
    0.06
    .Syntax
    0.06
     rece
    0.06
    find
    0.06
     SAC
    0.06
     certif
    0.06
     cliff
    0.06
    Act Density 0.336%

    No Known Activations