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
    .AR
    -0.07
    rar
    -0.07
    )].
    -0.07
    ”。
    -0.07
    "How
    -0.06
     Gür
    -0.06
    getConfig
    -0.06
    σκευή
    -0.06
     Gundam
    -0.06
    นาด
    -0.06
    POSITIVE LOGITS
     Flex
    0.06
     unemployed
    0.06
     correcting
    0.06
     Babylon
    0.06
    isser
    0.06
    	alpha
    0.06
     nause
    0.06
     Nikol
    0.06
     Listed
    0.06
     monsters
    0.06
    Act Density 0.000%

    No Known Activations