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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -photo
    -0.06
     culinary
    -0.06
     جنوبی
    -0.06
     Underground
    -0.06
    “My
    -0.06
    沈
    -0.06
     specials
    -0.06
     Rever
    -0.06
     fluent
    -0.06
     mực
    -0.06
    POSITIVE LOGITS
    OME
    0.07
    opp
    0.06
    afen
    0.06
    _TER
    0.06
     Symbol
    0.06
     клу
    0.06
     resetting
    0.06
    uD
    0.06
    _DOC
    0.06
    ANGES
    0.06
    Act Density 0.006%

    No Known Activations