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

    Neuronpedia

    INDEX
    Explanations

    '

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pady
    -0.06
    (lang
    -0.06
    ặ
    -0.06
     <+
    -0.06
    omething
    -0.06
    .balance
    -0.06
    (side
    -0.06
    But
    -0.06
     chaired
    -0.06
    據
    -0.05
    POSITIVE LOGITS
    �
    0.07
     предвар
    0.07
     Mojo
    0.06
    Simply
    0.06
     участие
    0.06
     Persons
    0.06
    PJ
    0.06
     proclamation
    0.06
    Iron
    0.06
     siyasi
    0.06
    Act Density 0.000%

    No Known Activations