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

    Neuronpedia

    INDEX
    Explanations

    except for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dist
    -0.07
    	us
    -0.06
    .et
    -0.06
     ayrıntılı
    -0.06
    .databind
    -0.06
     improperly
    -0.06
    jq
    -0.06
    backgroundColor
    -0.06
     kendisine
    -0.06
     Richie
    -0.06
    POSITIVE LOGITS
     except
    0.07
    haven
    0.07
    ी.
    0.07
    اعي
    0.07
     Artists
    0.06
    رج
    0.06
    side
    0.06
    SN
    0.06
     pár
    0.06
    ')->
    0.06
    Act Density 0.039%

    No Known Activations