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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     picnic
    -0.06
    	pool
    -0.06
    (pm
    -0.06
    Availability
    -0.06
     naam
    -0.06
     Indianapolis
    -0.06
     náz
    -0.06
     sư
    -0.06
     envi
    -0.06
    τικά
    -0.06
    POSITIVE LOGITS
     очеред
    0.07
     MAG
    0.06
    -upload
    0.06
     ledger
    0.06
    누
    0.06
     ＿
    0.06
    emap
    0.06
    AccessType
    0.06
    فس
    0.06
     Alger
    0.06
    Act Density 0.048%

    No Known Activations