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

    Neuronpedia

    INDEX
    Explanations

    By

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    community
    -0.07
     beam
    -0.07
     humanitarian
    -0.06
    dar
    -0.06
     深
    -0.06
    Career
    -0.06
     Tutorial
    -0.06
     Ricky
    -0.06
     Beam
    -0.06
    Tabs
    -0.06
    POSITIVE LOGITS
     �
    0.06
    ARD
    0.06
     Bras
    0.06
    enez
    0.06
    getitem
    0.06
     NotFoundException
    0.06
     بای
    0.06
    (NS
    0.05
    lease
    0.05
    (std
    0.05
    Act Density 0.026%

    No Known Activations