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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ihrer
    -0.07
     lên
    -0.06
    नल
    -0.06
    _by
    -0.06
    _TP
    -0.06
     ActivatedRoute
    -0.06
    submission
    -0.06
     halten
    -0.06
    -source
    -0.06
    logo
    -0.06
    POSITIVE LOGITS
    distributed
    0.07
    (土
    0.06
    (shift
    0.06
    (before
    0.06
      ↵↵
    0.06
     Mondays
    0.06
    @Slf
    0.06
    سته
    0.06
     spanning
    0.06
    	work
    0.06
    Act Density 0.016%

    No Known Activations