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

    Neuronpedia

    INDEX
    Explanations

    proof

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wagner
    -0.08
     eccentric
    -0.07
     Campus
    -0.07
    _TOUCH
    -0.07
    lobe
    -0.07
    ONLY
    -0.07
     Tags
    -0.07
    _period
    -0.07
    墙上
    -0.07
     tây
    -0.06
    POSITIVE LOGITS
    إسلام
    0.07
    🎓
    0.07
    ื
    0.07
    防水
    0.07
     Professionals
    0.07
     proof
    0.06
     혹
    0.06
     Sly
    0.06
     RaisePropertyChanged
    0.06
     Chu
    0.06
    Act Density 0.007%

    No Known Activations