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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CE
    -0.06
     bi
    -0.06
     İb
    -0.06
    velope
    -0.06
     قل
    -0.06
     Kills
    -0.06
    ksen
    -0.06
     recurs
    -0.06
    riteria
    -0.06
     poprvé
    -0.05
    POSITIVE LOGITS
    annah
    0.07
     endl
    0.07
    doubleValue
    0.07
     Eduardo
    0.07
    σφα
    0.07
    orthand
    0.06
    울
    0.06
     etkili
    0.06
     Avatar
    0.06
     Saud
    0.06
    Act Density 0.154%

    No Known Activations