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

    Neuronpedia

    INDEX
    Explanations

    comedy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     женщина
    -0.07
     Garrison
    -0.07
    реш
    -0.06
     difer
    -0.06
     declare
    -0.06
    Ek
    -0.06
     часом
    -0.06
    _SERVER
    -0.06
     hbox
    -0.06
    _tokens
    -0.06
    POSITIVE LOGITS
    .SUCCESS
    0.06
    �
    0.06
     příst
    0.06
    ...',
    0.06
    Liverpool
    0.06
    ंप
    0.06
     manipulation
    0.06
    	bg
    0.06
    .getAttribute
    0.06
     đài
    0.06
    Act Density 0.025%

    No Known Activations