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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     studies
    -0.07
     lodging
    -0.07
     cil
    -0.06
     cyst
    -0.06
     Toronto
    -0.06
    etrofit
    -0.06
     warmed
    -0.06
    Toronto
    -0.06
     영국
    -0.06
    itted
    -0.06
    POSITIVE LOGITS
     SUCH
    0.07
    isSelected
    0.07
     داشتن
    0.06
     pozem
    0.06
    (WIN
    0.06
     iid
    0.06
     øns
    0.06
    buch
    0.06
    _WEAPON
    0.06
     honoring
    0.06
    Act Density 0.018%

    No Known Activations