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

    Neuronpedia

    INDEX
    Explanations

    software code packages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Debug
    -0.07
     покол
    -0.06
    _planes
    -0.06
    Ionic
    -0.06
    .FragmentManager
    -0.06
     melts
    -0.06
    िव
    -0.06
     sued
    -0.06
    Deg
    -0.06
     hometown
    -0.06
    POSITIVE LOGITS
     `$
    0.07
    (add
    0.07
     Honda
    0.06
    ıyoruz
    0.06
     jTable
    0.06
    ınıza
    0.06
    -password
    0.06
    خم
    0.06
     laure
    0.06
     quienes
    0.06
    Act Density 0.039%

    No Known Activations