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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bella
    -0.07
    اعي
    -0.07
     anal
    -0.07
     rooftop
    -0.07
     Orb
    -0.06
     GSL
    -0.06
    ласти
    -0.06
     locker
    -0.06
     mindset
    -0.06
    (INFO
    -0.06
    POSITIVE LOGITS
    vou
    0.07
     Flower
    0.07
     yönetim
    0.07
     daycare
    0.06
     verir
    0.06
     storyboard
    0.06
     correctness
    0.06
    迪
    0.06
    _THAN
    0.06
    _clicked
    0.06
    Act Density 0.038%

    No Known Activations