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

    Neuronpedia

    INDEX
    Explanations

    Examples and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     workers
    -0.07
    onds
    -0.07
    Partner
    -0.06
     застосування
    -0.06
     unary
    -0.06
    USA
    -0.06
     rut
    -0.06
     worker
    -0.06
     Observatory
    -0.06
     dab
    -0.06
    POSITIVE LOGITS
    _Msk
    0.07
     ];
↵
    0.07
    *l
    0.06
     нарез
    0.06
    £o
    0.06
     sä
    0.06
    insics
    0.06
     명
    0.06
     khắc
    0.06
    acci
    0.06
    Act Density 0.010%

    No Known Activations