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

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _caps
    -0.07
    Eq
    -0.07
    Sensitive
    -0.06
    _Id
    -0.06
     ポ
    -0.06
     Dwight
    -0.06
     GObject
    -0.06
    ＝
    -0.06
     asshole
    -0.06
    <Q
    -0.06
    POSITIVE LOGITS
     doprov
    0.07
    	sys
    0.06
    recommended
    0.06
     lasts
    0.06
     fastest
    0.06
     ieee
    0.06
     ув
    0.06
    India
    0.06
    жив
    0.06
     Breast
    0.06
    Act Density 0.000%

    No Known Activations