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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     X
    -0.07
    /status
    -0.06
     facilitated
    -0.06
     wich
    -0.06
     RETURN
    -0.06
     civil
    -0.06
     dude
    -0.06
     Death
    -0.06
    相關
    -0.06
     mening
    -0.06
    POSITIVE LOGITS
    (pointer
    0.07
    餐
    0.06
    ΙΛ
    0.06
    okie
    0.06
    .le
    0.06
    achelor
    0.06
    ปก
    0.06
    एम
    0.06
     Daisy
    0.06
    글상위
    0.06
    Act Density 0.007%

    No Known Activations