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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rac
    -0.07
     полот
    -0.07
     план
    -0.07
    ्यव
    -0.07
     caravan
    -0.06
    modified
    -0.06
     gardens
    -0.06
    �
    -0.06
    /package
    -0.06
    icos
    -0.06
    POSITIVE LOGITS
     relaciones
    0.07
     Excellent
    0.07
    raits
    0.06
     SHIPPING
    0.06
    Hack
    0.06
     miejsc
    0.06
    ologna
    0.06
    isinde
    0.06
     Gn
    0.06
    (audio
    0.06
    Act Density 0.019%

    No Known Activations