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

    Neuronpedia

    INDEX
    Explanations

    references and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     Sh
    -0.06
    -c
    -0.06
    ipated
    -0.06
     HBO
    -0.06
    ują
    -0.06
     mentioned
    -0.06
    .substr
    -0.06
    (begin
    -0.06
     अगस
    -0.06
    POSITIVE LOGITS
    izard
    0.07
     刘
    0.07
    .tiles
    0.06
    	Key
    0.06
     Obl
    0.06
     frightened
    0.06
     �
    0.06
     alarm
    0.06
    _weight
    0.06
     wirklich
    0.06
    Act Density 0.005%

    No Known Activations