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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wis
    -0.07
     erf
    -0.06
     thaw
    -0.06
     Scots
    -0.06
     işlet
    -0.06
     firm
    -0.06
    AVIS
    -0.06
    ươi
    -0.06
    WindowText
    -0.06
     pigs
    -0.06
    POSITIVE LOGITS
    [right
    0.07
    启
    0.07
    .ul
    0.07
     основных
    0.07
    ια
    0.06
    μένα
    0.06
    .land
    0.06
    $temp
    0.06
     安
    0.06
    0.06
    Act Density 0.001%

    No Known Activations