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

    Neuronpedia

    INDEX
    Explanations

    User Interfaces or Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decorate
    -0.09
    Bil
    -0.08
    decor
    -0.08
     mej
    -0.08
     bil
    -0.08
     ಮಂದಿ
    -0.08
    amiento
    -0.07
     Verbesserung
    -0.07
     primeros
    -0.07
     oversized
    -0.07
    POSITIVE LOGITS
     asupra
    0.09
    /API
    0.07
    vorming
    0.07
    /support
    0.07
     leaked
    0.07
     부탁
    0.07
    	Data
    0.07
     juices
    0.07
    odata
    0.07
     einge
    0.07
    Act Density 0.041%

    No Known Activations