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

    Neuronpedia

    INDEX
    Explanations

    influential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    892
    -0.07
    amework
    -0.07
    َان
    -0.07
    'all
    -0.06
    雷
    -0.06
    (rec
    -0.06
    辛
    -0.06
    Safe
    -0.06
    ’all
    -0.06
     newPassword
    -0.06
    POSITIVE LOGITS
    _Blue
    0.07
     royal
    0.07
     &=
    0.06
    ampionship
    0.06
    елей
    0.06
     Redskins
    0.06
     scraping
    0.06
    phalt
    0.06
     chví
    0.06
    roach
    0.06
    Act Density 0.027%

    No Known Activations