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

    Neuronpedia

    INDEX
    Explanations

    exceptions and meteors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шуда
    -0.08
    Lemma
    -0.08
     Remark
    -0.08
    Remark
    -0.08
    па
    -0.08
     sabab
    -0.08
    шы
    -0.07
     Markle
    -0.07
     quadru
    -0.07
    remark
    -0.07
    POSITIVE LOGITS
     colorful
    0.08
    łos
    0.08
     operational
    0.08
     عد
    0.08
     dyed
    0.08
     vooral
    0.08
     económ
    0.08
     spectacle
    0.07
     lively
    0.07
     spectacles
    0.07
    Act Density 0.001%

    No Known Activations