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

    Neuronpedia

    INDEX
    Explanations

    placenta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rig
    -0.08
    	private
    -0.07
     dank
    -0.07
    цю
    -0.06
    ог
    -0.06
    OLF
    -0.06
     Chamber
    -0.06
    amber
    -0.06
     rifles
    -0.06
    权
    -0.06
    POSITIVE LOGITS
    (steps
    0.07
     ｉ
    0.07
    (space
    0.06
    êt
    0.06
    (dictionary
    0.06
     Depart
    0.06
    <String
    0.06
     Comey
    0.06
     Previously
    0.06
     approve
    0.06
    Act Density 0.001%

    No Known Activations