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

    Neuronpedia

    INDEX
    Explanations

    doesn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     progressives
    -0.07
    p
    -0.06
    Notify
    -0.06
    Republicans
    -0.06
    AX
    -0.06
    /net
    -0.06
    _attachments
    -0.06
     analyses
    -0.06
     acquisition
    -0.06
    аних
    -0.06
    POSITIVE LOGITS
    habit
    0.07
     //{
↵
    0.07
    κας
    0.06
    (gray
    0.06
    		
↵		
↵
    0.06
    pheres
    0.06
     الشي
    0.06
    Elect
    0.06
    _MET
    0.06
     αν
    0.06
    Act Density 0.068%

    No Known Activations