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

    Neuronpedia

    INDEX
    Explanations

    ///

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fat
    -0.07
     kra
    -0.07
    ad
    -0.07
    arris
    -0.07
    AREA
    -0.07
    риз
    -0.07
    оруж
    -0.07
    588
    -0.07
    fat
    -0.07
     Maggie
    -0.06
    POSITIVE LOGITS
    ///<
    0.08
    ///↵
    0.07
    ///
    0.07
     ///↵
    0.07
     JV
    0.07
     Pavilion
    0.07
     Trip
    0.07
    ारण
    0.07
     Hub
    0.07
     Conj
    0.07
    Act Density 0.008%

    No Known Activations