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

    Neuronpedia

    INDEX
    Explanations

    Toughening up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    []){↵
    -0.07
    nam
    -0.07
     suspicious
    -0.07
     tremend
    -0.06
    _location
    -0.06
     pak
    -0.06
     wouldn
    -0.06
    ัล
    -0.06
     ран
    -0.06
     мож
    -0.06
    POSITIVE LOGITS
    	email
    0.07
    >Email
    0.07
    (bottom
    0.07
    Frames
    0.07
    مود
    0.07
     combinations
    0.06
     annual
    0.06
     Logout
    0.06
     Meditation
    0.06
    Bitmap
    0.06
    Act Density 0.072%

    No Known Activations