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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ském
    -0.07
     piercing
    -0.07
    Empty
    -0.07
    视频
    -0.07
    Rob
    -0.07
    places
    -0.07
    thesized
    -0.06
    nému
    -0.06
    PRS
    -0.06
    ♡
    -0.06
    POSITIVE LOGITS
     known
    0.08
    known
    0.07
     Known
    0.06
     mun
    0.06
     writings
    0.06
    Expected
    0.06
     }}}
    0.06
     internally
    0.06
     klar
    0.06
     bekan
    0.06
    Act Density 0.016%

    No Known Activations