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

    Neuronpedia

    INDEX
    Explanations

    LLVM IR numerical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ရေ
    0.35
    segaretro
    0.34
    ोरा
    0.34
    یرے
    0.34
     Fleurit
    0.34
     vitre
    0.34
     outcrops
    0.34
     Southport
    0.33
    LOTREntity
    0.33
     adiabatically
    0.33
    POSITIVE LOGITS
    1
    0.40
     Expression
    0.37
     m
    0.35
     type
    0.35
     conf
    0.35
    Class
    0.34
     Type
    0.33
    ad
    0.33
    Type
    0.33
     State
    0.33
    Act Density 0.001%

    No Known Activations