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

    Neuronpedia

    INDEX
    Explanations

    budget cuts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fraudulent
    -0.07
     cylinders
    -0.07
    \Tests
    -0.06
     配
    -0.06
    Checker
    -0.06
     maxWidth
    -0.06
    _credentials
    -0.06
    etCode
    -0.06
     saber
    -0.06
    چی
    -0.06
    POSITIVE LOGITS
     antidepress
    0.06
     butter
    0.06
     gastro
    0.06
    (boost
    0.06
     przy
    0.06
     hashed
    0.06
    .assert
    0.06
    ใน
    0.06
    ilar
    0.06
    ﻠ
    0.06
    Act Density 0.063%

    No Known Activations