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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valentine
    0.43
    ască
    0.39
    indelijk
    0.39
     sql
    0.38
     xp
    0.38
    Warner
    0.38
     bxc
    0.38
     dilemma
    0.38
    роки
    0.38
    Valentine
    0.37
    POSITIVE LOGITS
     qualified
    0.63
     Numeric
    0.44
    Numeric
    0.44
     квали
    0.44
    qualified
    0.43
     Graphics
    0.41
     Moj
    0.40
     Technik
    0.40
     Προ
    0.40
     Vehicles
    0.39
    Act Density 0.000%

    No Known Activations