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

    Neuronpedia

    INDEX
    Explanations

    demonstrating categories words think paragraph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чите
    0.44
    чень
    0.42
    TabIndex
    0.41
    と共に
    0.41
     tangents
    0.40
    חוז
    0.40
     equalities
    0.40
    checkable
    0.39
    تالي
    0.39
     injectors
    0.39
    POSITIVE LOGITS
    met
    0.48
    órica
    0.45
     solder
    0.43
    är
    0.43
    orous
    0.43
    rika
    0.42
    urent
    0.42
    eksi
    0.42
    enden
    0.41
     Alex
    0.41
    Act Density 0.002%

    No Known Activations