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

    Neuronpedia

    INDEX
    Explanations

    URLs and technical references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     himself
    -0.07
    	inter
    -0.07
     gods
    -0.07
    PLAN
    -0.07
     conform
    -0.06
     understood
    -0.06
    (end
    -0.06
     welcomed
    -0.06
     آس
    -0.06
    imgs
    -0.06
    POSITIVE LOGITS
    ♀♀
    0.06
     vacc
    0.06
     GameManager
    0.06
     jobId
    0.06
    .FromSeconds
    0.06
     Sabb
    0.06
    ạch
    0.06
    _bi
    0.06
    ọt
    0.06
    beth
    0.06
    Act Density 0.088%

    No Known Activations