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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .St
    -0.07
     morning
    -0.07
    [array
    -0.07
    /loader
    -0.07
    .ls
    -0.07
     가
    -0.07
     tiên
    -0.06
     playback
    -0.06
     Aph
    -0.06
     Hero
    -0.06
    POSITIVE LOGITS
    phen
    0.07
    歳
    0.07
     detain
    0.06
    兒
    0.06
    -trash
    0.06
    phyl
    0.06
     Vulkan
    0.06
    benh
    0.06
    εις
    0.06
    assic
    0.06
    Act Density 0.010%

    No Known Activations