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

    Neuronpedia

    INDEX
    Explanations

    headquartered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flotation
    -0.07
     숨
    -0.06
    lerin
    -0.06
    CREASE
    -0.06
    ￣￣￣￣
    -0.06
     sollten
    -0.06
    驚
    -0.06
     tắt
    -0.06
    τέλε
    -0.06
    айте
    -0.06
    POSITIVE LOGITS
     headquartered
    0.08
     Hof
    0.07
     Rw
    0.07
    reso
    0.06
     hp
    0.06
     민주
    0.06
     Swinger
    0.06
    以外
    0.06
    heimer
    0.06
     Bd
    0.06
    Act Density 0.009%

    No Known Activations