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

    Neuronpedia

    INDEX
    Explanations

    understanding, improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     аг
    -0.07
    ДА
    -0.07
     Fuller
    -0.07
    angent
    -0.07
    더
    -0.06
    .entity
    -0.06
    _usage
    -0.06
     Postal
    -0.06
     Guidance
    -0.06
     phá
    -0.06
    POSITIVE LOGITS
    ощи
    0.06
    {/*
    0.06
    [slot
    0.06
     aval
    0.06
    0.06
    ...";↵
    0.06
    ่น
    0.06
    [sub
    0.06
    =l
    0.06
     brushed
    0.06
    Act Density 0.109%

    No Known Activations