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

    Neuronpedia

    INDEX
    Explanations

    heat treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ところ
    -0.07
     objetivo
    -0.07
     Reno
    -0.06
    Lo
    -0.06
    üslüman
    -0.06
     Flag
    -0.06
    /
↵
↵
    -0.06
    .Matrix
    -0.06
     Query
    -0.06
     однако
    -0.06
    POSITIVE LOGITS
    .libs
    0.07
    (strict
    0.07
     roadway
    0.06
    ської
    0.06
    rit
    0.06
     textbox
    0.06
    ΟΓ
    0.06
     wiel
    0.06
    .Many
    0.06
    -ext
    0.06
    Act Density 0.054%

    No Known Activations