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

    Neuronpedia

    INDEX
    Explanations

    consulting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ethernet
    -0.07
     fixing
    -0.06
    θή
    -0.06
    ül
    -0.06
     illumination
    -0.06
    amento
    -0.06
    Imagen
    -0.06
     allocator
    -0.06
     Rape
    -0.06
    sets
    -0.06
    POSITIVE LOGITS
    .ShouldBe
    0.07
    :return
    0.07
    )((
    0.07
     skyrocket
    0.06
     Kč
    0.06
    =$_
    0.06
    getToken
    0.06
    kovou
    0.06
     '}';↵
    0.06
    '])->
    0.06
    Act Density 0.120%

    No Known Activations