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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /default
    -0.08
    .related
    -0.07
    搜
    -0.07
    .part
    -0.07
    (Common
    -0.06
    技
    -0.06
     unl
    -0.06
    -terrorism
    -0.06
     Wish
    -0.06
     wax
    -0.06
    POSITIVE LOGITS
    uisse
    0.07
    atherine
    0.07
    raig
    0.06
    ensaje
    0.06
     vara
    0.06
                        ↵
    0.06
     satisfy
    0.06
     brasile
    0.06
     uttered
    0.06
    们
    0.06
    Act Density 0.089%

    No Known Activations