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

    Neuronpedia

    INDEX
    Explanations

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ülü
    -0.07
     Tuy
    -0.07
    ttp
    -0.07
     Jin
    -0.06
    меч
    -0.06
     tek
    -0.06
    _tooltip
    -0.06
    Trip
    -0.06
    Qué
    -0.06
     sử
    -0.06
    POSITIVE LOGITS
     शत
    0.06
    .Active
    0.06
     flick
    0.06
    !»
    0.06
     Writes
    0.06
     settles
    0.06
     norge
    0.06
    LLLL
    0.06
     receptor
    0.06
     anatom
    0.06
    Act Density 0.002%

    No Known Activations