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
     aspire
    -0.09
    inclusive
    -0.08
    iterate
    -0.08
     monetize
    -0.08
     ജനറ
    -0.08
    жем
    -0.08
    ബ്ര
    -0.08
    allinen
    -0.08
     nachhaltig
    -0.08
    They're
    -0.08
    POSITIVE LOGITS
     veranderen
    0.08
    肩
    0.08
     बातें
    0.08
     nye
    0.08
     घूम
    0.08
     verandert
    0.08
     أصبح
    0.08
     बने
    0.07
     नए
    0.07
    侧
    0.07
    Act Density 0.015%

    No Known Activations