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

    Neuronpedia

    INDEX
    Explanations

    subject matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ping
    -0.06
     Luo
    -0.06
    llll
    -0.06
     Teaching
    -0.06
     poetic
    -0.06
    to
    -0.06
     Saturday
    -0.06
     Typically
    -0.06
                                            ↵
    -0.06
    Thursday
    -0.06
    POSITIVE LOGITS
    removeAttr
    0.07
    冠
    0.06
     gluc
    0.06
     entirety
    0.06
    -Isl
    0.06
    (cm
    0.06
    idth
    0.06
     Haskell
    0.06
     Πρό
    0.06
    .initialize
    0.06
    Act Density 0.027%

    No Known Activations