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

    Neuronpedia

    INDEX
    Explanations

    scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Set
    -0.06
     SetUp
    -0.06
    .SimpleDateFormat
    -0.06
    Charlie
    -0.06
    าของ
    -0.06
     buys
    -0.06
    乾
    -0.06
     başlam
    -0.06
    Subsystem
    -0.06
     prostor
    -0.06
    POSITIVE LOGITS
     generally
    0.07
    AINED
    0.06
    terror
    0.06
    unned
    0.06
    _white
    0.06
     이것
    0.06
    elligence
    0.06
    ệ
    0.06
     Such
    0.06
    (aa
    0.06
    Act Density 0.007%

    No Known Activations