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

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngân
    -0.07
    ظيف
    -0.07
    .ls
    -0.06
     gloss
    -0.06
    copies
    -0.06
     Inn
    -0.06
     Giul
    -0.06
     lvl
    -0.06
    decrypt
    -0.06
    $l
    -0.06
    POSITIVE LOGITS
     Triple
    0.06
     настоя
    0.06
     watchdog
    0.06
     afflicted
    0.06
     eyewitness
    0.06
     indeed
    0.06
    _det
    0.06
     keyboards
    0.06
    figures
    0.06
     Tina
    0.06
    Act Density 0.137%

    No Known Activations