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

    Neuronpedia

    INDEX
    Explanations

    Explaining an issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ONLY
    -0.07
    operators
    -0.06
    _scope
    -0.06
     Atlantis
    -0.06
     condoms
    -0.06
    _decoder
    -0.06
     hygiene
    -0.06
    ータ
    -0.06
     NSUInteger
    -0.06
    Zen
    -0.06
    POSITIVE LOGITS
    �
    0.08
     opportunities
    0.07
    ázd
    0.07
     («
    0.06
     reins
    0.06
     přesvěd
    0.06
    ít
    0.06
     vill
    0.06
    sylvania
    0.06
    !");↵
    0.06
    Act Density 0.025%

    No Known Activations