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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unreal
    -0.08
     Chand
    -0.07
     "↵↵
    -0.06
     ils
    -0.06
     mash
    -0.06
    (Line
    -0.06
    	actual
    -0.06
    (reg
    -0.06
    (SC
    -0.06
     со
    -0.06
    POSITIVE LOGITS
    izoph
    0.07
    "]==
    0.07
     prosecutions
    0.07
     результат
    0.06
     improvements
    0.06
    addField
    0.06
     addChild
    0.06
     بررسی
    0.06
    workflow
    0.06
    probability
    0.06
    Act Density 0.039%

    No Known Activations