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

    Neuronpedia

    INDEX
    Explanations

    contain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ἄ
    -0.07
     exceedingly
    -0.07
    枉
    -0.07
    \Repository
    -0.07
    localized
    -0.07
     escaping
    -0.07
    噻
    -0.07
    (plane
    -0.07
     Trent
    -0.07
    _HAVE
    -0.06
    POSITIVE LOGITS
    Ḟ
    0.07
    最も
    0.06
     sum
    0.06
    wed
    0.06
     cheers
    0.06
     laten
    0.06
    薪资
    0.06
     Gets
    0.06
    .Width
    0.06
    Targets
    0.06
    Act Density 0.040%

    No Known Activations