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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dou
    -0.07
     Christoph
    -0.06
     nouve
    -0.06
     orbital
    -0.06
     callable
    -0.06
     adverts
    -0.06
    	org
    -0.06
    occus
    -0.06
     clutch
    -0.06
     oscillator
    -0.06
    POSITIVE LOGITS
    №№
    0.08
    ्गत
    0.07
     ไป
    0.07
     ""},↵
    0.07
    ี้↵
    0.07
     hemp
    0.07
    靠
    0.07
     ESPN
    0.07
    xBD
    0.06
     knex
    0.06
    Act Density 0.013%

    No Known Activations