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

    Neuronpedia

    INDEX
    Explanations

    tr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孚
    -0.07
     |\
    -0.07
    ⓑ
    -0.07
     tipped
    -0.07
    桐
    -0.07
    .Len
    -0.07
     diminished
    -0.07
    值班
    -0.07
    ĩ
    -0.07
     clientId
    -0.06
    POSITIVE LOGITS
    company
    0.08
     stainless
    0.07
    出来
    0.07
    WebDriver
    0.07
    (cat
    0.07
     görüyor
    0.07
     Canary
    0.07
     Haskell
    0.07
    /Linux
    0.07
    AMERA
    0.07
    Act Density 0.002%

    No Known Activations