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

    Neuronpedia

    INDEX
    Explanations

    Forum/discussion questions or posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LGBT
    -0.06
     interesse
    -0.06
    alloween
    -0.06
     noci
    -0.06
    factory
    -0.06
     Peng
    -0.06
    _air
    -0.06
     isSuccess
    -0.06
    ={$
    -0.06
    adresse
    -0.06
    POSITIVE LOGITS
    ethylene
    0.08
     сх
    0.07
    يدة
    0.07
     کسانی
    0.07
     موس
    0.06
     pad
    0.06
     rumor
    0.06
    ắp
    0.06
     //↵
    0.06
    YTE
    0.06
    Act Density 0.037%

    No Known Activations