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

    Neuronpedia

    INDEX
    Explanations

    regulations and law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quarter
    -0.07
    Leader
    -0.07
    Emitter
    -0.07
    .userId
    -0.07
    _CHARACTER
    -0.06
    TRANSFER
    -0.06
    Product
    -0.06
    	s
    -0.06
    (header
    -0.06
    _console
    -0.06
    POSITIVE LOGITS
     deny
    0.07
    omi
    0.06
    měr
    0.06
    �
    0.06
    黒
    0.06
     physiological
    0.06
    щини
    0.06
    blockquote
    0.06
    วม
    0.06
     consideration
    0.06
    Act Density 0.048%

    No Known Activations