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

    Neuronpedia

    INDEX
    Explanations

    MainActivity class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     T
    0.40
     verific
    0.39
     ناق
    0.39
    Soil
    0.39
     V
    0.38
     خاک
    0.38
     बेबी
    0.38
    гули
    0.38
     చర్చ
    0.38
    而不
    0.37
    POSITIVE LOGITS
     circled
    0.48
    rei
    0.44
    circled
    0.40
    σει
    0.39
    idae
    0.38
     debacle
    0.37
     Lett
    0.37
    jach
    0.37
    ondata
    0.37
    igure
    0.36
    Act Density 0.000%

    No Known Activations