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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     applicant
    -0.07
     卡
    -0.07
     interval
    -0.07
    空
    -0.06
    ील
    -0.06
     pier
    -0.06
    альному
    -0.06
    ioxide
    -0.06
     shoes
    -0.06
     impost
    -0.06
    POSITIVE LOGITS
    __.'/
    0.07
     VERBOSE
    0.06
    wcsstore
    0.06
     Ease
    0.06
    〔
    0.06
    ,it
    0.06
    Battle
    0.06
    	dialog
    0.06
     vàng
    0.06
    >'+↵
    0.06
    Act Density 0.383%

    No Known Activations