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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    흥
    -0.06
    ROUTE
    -0.06
    )null
    -0.06
    earned
    -0.06
     storyt
    -0.06
    رت
    -0.06
    Cog
    -0.06
     döndü
    -0.06
    (up
    -0.06
     definite
    -0.06
    POSITIVE LOGITS
    _radio
    0.07
    ологія
    0.07
     Ivanka
    0.06
    �
    0.06
     tribute
    0.06
     cooks
    0.06
     Filipino
    0.06
     fingertips
    0.06
    osloven
    0.06
     하면
    0.06
    Act Density 0.009%

    No Known Activations