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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    едини
    -0.06
    ца
    -0.06
    .Queue
    -0.06
    isol
    -0.06
    зем
    -0.06
    oč
    -0.06
    mere
    -0.06
    bling
    -0.06
    cal
    -0.06
    chemical
    -0.06
    POSITIVE LOGITS
     Babylon
    0.07
    ONUS
    0.07
    _distribution
    0.07
     ﻣ
    0.06
    lord
    0.06
     Gig
    0.06
    osen
    0.06
     suspicions
    0.06
    .Take
    0.06
     üzere
    0.06
    Act Density 0.000%

    No Known Activations