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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מס
    -0.08
     ספ
    -0.08
    plements
    -0.07
     представить
    -0.07
     നൽകി
    -0.07
    ితో
    -0.07
    Approve
    -0.07
     charme
    -0.07
    제
    -0.07
     подтверж
    -0.07
    POSITIVE LOGITS
     betur
    0.08
    #g
    0.07
     #####
    0.07
     även
    0.07
     顺
    0.07
     relinqu
    0.07
     enduring
    0.07
     onward
    0.07
    abilecek
    0.07
     kommenden
    0.07
    Act Density 0.000%

    No Known Activations