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

    Neuronpedia

    INDEX
    Explanations

    brew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allowed
    -0.08
    Feedback
    -0.08
    _feedback
    -0.08
     feedback
    -0.08
    feedback
    -0.07
     bothering
    -0.07
    speech
    -0.07
     ту
    -0.07
     الدراسة
    -0.07
     عدة
    -0.07
    POSITIVE LOGITS
     semper
    0.10
     Sidebar
    0.10
     chama
    0.09
    (pkg
    0.09
     llvm
    0.08
     menjal
    0.08
     ચલ
    0.08
     jardin
    0.08
     arteries
    0.08
     લી
    0.08
    Act Density 0.001%

    No Known Activations