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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evaluate
    -0.07
    手に
    -0.07
     phái
    -0.07
    	tb
    -0.07
    matches
    -0.07
     detective
    -0.06
    _decl
    -0.06
     ngắn
    -0.06
     vat
    -0.06
     عامل
    -0.06
    POSITIVE LOGITS
    еви
    0.07
    .persist
    0.06
    .
↵
↵
    0.06
    (locations
    0.06
    _spectrum
    0.06
    containers
    0.06
     authDomain
    0.06
    antine
    0.05
     blocked
    0.05
    atter
    0.05
    Act Density 0.015%

    No Known Activations