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

    Neuronpedia

    INDEX
    Explanations

    instruction adherence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    푥
    0.46
     THROUGH
    0.42
    ற்றம்
    0.41
     souha
    0.40
     WILLIAMS
    0.40
     communicate
    0.40
    룔
    0.39
     bettors
    0.39
     TEX
    0.39
     でしょう
    0.39
    POSITIVE LOGITS
     Plan
    0.41
    Trip
    0.39
     Trip
    0.39
    Watch
    0.38
    ent
    0.38
     Act
    0.38
     सक्सेना
    0.37
    Mesh
    0.37
    venture
    0.37
    पुरा
    0.37
    Act Density 0.000%

    No Known Activations