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

    Neuronpedia

    INDEX
    Explanations

    inches wide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Temper
    0.39
     lifespan
    0.38
     timepiece
    0.38
     functions
    0.37
     projects
    0.37
     beloved
    0.36
     attitude
    0.36
     furnishing
    0.35
     interface
    0.35
     interfaces
    0.35
    POSITIVE LOGITS
     gratuitamente
    0.39
    Ukraine
    0.38
    ỗng
    0.38
    のではなく
    0.38
     Ukraina
    0.37
    FBSDK
    0.37
    deprecation
    0.37
     Verónica
    0.36
    Ꭴ
    0.36
    णा
    0.36
    Act Density 0.002%

    No Known Activations