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

    Neuronpedia

    INDEX
    Explanations

    European Union

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Harry
    -0.08
     ench
    -0.08
    TRAN
    -0.07
     corro
    -0.07
     goofy
    -0.07
    esz
    -0.07
     Batter
    -0.07
     kits
    -0.07
    .Fetch
    -0.07
     Fuji
    -0.07
    POSITIVE LOGITS
    .location
    0.08
     LB
    0.07
     Ла
    0.07
    רפא
    0.07
     중요
    0.07
    LABEL
    0.06
    External
    0.06
    Squared
    0.06
    ::_('
    0.06
    SCRIBE
    0.06
    Act Density 0.032%

    No Known Activations