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

    Neuronpedia

    INDEX
    Explanations

    code and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ƒ
    0.42
    ufu
    0.38
    ᅳ
    0.37
     ሀ
    0.36
    FLU
    0.36
    বন্দর
    0.36
    IamPermissions
    0.36
    ᓪ
    0.36
    loadFile
    0.34
    <0x8C>
    0.34
    POSITIVE LOGITS
     execution
    0.43
     unlikely
    0.42
     eficiencia
    0.39
     эта
    0.38
     skipping
    0.37
     gerçekleş
    0.37
     unimportant
    0.37
     luxury
    0.37
     ascending
    0.37
     efficiency
    0.36
    Act Density 0.051%

    No Known Activations