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

    Neuronpedia

    INDEX
    Explanations

    theoretical physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rightly
    -0.07
    ("---
    -0.07
     unicorn
    -0.07
     curious
    -0.06
     zásob
    -0.06
    �
    -0.06
    方面
    -0.06
    _Runtime
    -0.06
    _RAM
    -0.06
    Doctor
    -0.06
    POSITIVE LOGITS
    \Seeder
    0.06
    ={}
    0.06
    |m
    0.06
    estination
    0.06
    ctrine
    0.06
     Phill
    0.06
     associate
    0.06
     alignItems
    0.06
    olicy
    0.06
    sterdam
    0.05
    Act Density 0.030%

    No Known Activations