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

    Neuronpedia

    INDEX
    Explanations

    Political titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALT
    -0.07
    173
    -0.06
    king
    -0.06
    _skills
    -0.06
    generator
    -0.06
     jednodu
    -0.06
    \Validation
    -0.06
    我們
    -0.06
    Ξ
    -0.06
     Pert
    -0.06
    POSITIVE LOGITS
     situ
    0.07
     آ
    0.06
     Med
    0.06
    	panic
    0.06
    ITIES
    0.06
     نادي
    0.06
    ="+
    0.06
     Vec
    0.06
     aggreg
    0.06
    .samples
    0.06
    Act Density 0.171%

    No Known Activations