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

    Neuronpedia

    INDEX
    Explanations

    Firefox, systems, lack, mountains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COL
    0.46
    o
    0.46
    ام
    0.44
    IST
    0.43
     Offset
    0.43
    8
    0.43
    al
    0.42
     Doubles
    0.42
     Kf
    0.42
    l
    0.42
    POSITIVE LOGITS
    보다는
    0.52
    ดิจ
    0.50
     केलेले
    0.49
     bohemian
    0.48
     despot
    0.48
     denim
    0.48
     uglify
    0.47
     elliptical
    0.47
     outsider
    0.47
    γή
    0.47
    Act Density 0.000%

    No Known Activations