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

    Neuronpedia

    INDEX
    Explanations

    proxy list, hath devoured

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modesty
    0.43
    refreshToken
    0.39
    myName
    0.39
    Banks
    0.39
     mandated
    0.38
    Bathroom
    0.38
    Mitchell
    0.38
    Synthetic
    0.37
    𝙻
    0.37
     Parry
    0.36
    POSITIVE LOGITS
    ዓ
    0.39
     grad
    0.37
     Ω
    0.37
     stumble
    0.37
     व्या
    0.37
     taper
    0.37
     স্থায়ী
    0.36
     collision
    0.36
    ೀಯ
    0.35
    挖
    0.35
    Act Density 0.001%

    No Known Activations