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

    Neuronpedia

    INDEX
    Explanations

    Web addresses, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freely
    -0.30
    å¦ĸ
    -0.27
    èħĶ
    -0.27
    ç«ĭä½ĵ
    -0.26
     exit
    -0.26
     pencil
    -0.26
     stereotype
    -0.25
     stere
    -0.25
    teil
    -0.25
    æľºç»Ħ
    -0.25
    POSITIVE LOGITS
    æİĸ
    0.27
     Himself
    0.24
    åĽŀèIJ½
    0.23
     PROGMEM
    0.23
     Guards
    0.23
    mary
    0.23
     dõi
    0.23
    æıIJä¾ĽåķĨ
    0.23
    ressed
    0.23
    åĪ¶éĢłåķĨ
    0.23
    Act Density 0.005%

    No Known Activations