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

    Neuronpedia

    INDEX
    Explanations

    version control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Southeast
    1.29
     hogar
    1.09
    Grat
    1.09
    ాతీయ
    1.08
     первым
    1.06
    Sexual
    1.05
    বারে
    1.04
    beautiful
    1.02
    MONGO
    1.01
     énerg
    1.00
    POSITIVE LOGITS
    en
    1.41
    ed
    1.36
    िक
    1.36
    ing
    1.35
     cognizant
    1.35
    ality
    1.28
    িং
    1.27
    ת
    1.27
    ة
    1.25
     reactants
    1.22
    Act Density 0.031%

    No Known Activations