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

    Neuronpedia

    INDEX
    Explanations

    medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irable
    -0.07
     GeForce
    -0.07
     JSGlobal
    -0.07
    JSGlobal
    -0.07
     Royale
    -0.06
    济
    -0.06
     alot
    -0.06
     Tower
    -0.06
    廳
    -0.06
     Blowjob
    -0.06
    POSITIVE LOGITS
     ett
    0.07
     cient
    0.07
    大量
    0.06
    μένο
    0.06
     Nested
    0.06
     bart
    0.06
     printed
    0.06
    statistics
    0.06
     kao
    0.06
    /d
    0.06
    Act Density 0.063%

    No Known Activations