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

    Neuronpedia

    INDEX
    Explanations

    SSRI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пу
    -0.07
     مکان
    -0.07
    LET
    -0.07
    uem
    -0.07
    ueue
    -0.07
     Institut
    -0.07
    ív
    -0.07
     modulus
    -0.06
    픈
    -0.06
    ót
    -0.06
    POSITIVE LOGITS
     SSR
    0.09
     dra
    0.07
     Kashmir
    0.06
     MLA
    0.06
     Enlight
    0.06
     violates
    0.06
    _sidebar
    0.06
     Imported
    0.06
    	Logger
    0.06
    .Blocks
    0.06
    Act Density 0.001%

    No Known Activations