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

    Neuronpedia

    INDEX
    Explanations

    Mixed text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SetProperty
    -0.06
     sacrifices
    -0.06
     nuit
    -0.06
     Pune
    -0.06
    QUIT
    -0.06
    (Expected
    -0.06
     <%
    -0.06
     kayıt
    -0.06
     Wohn
    -0.05
    ابه
    -0.05
    POSITIVE LOGITS
    कन
    0.07
     hunters
    0.07
    .imwrite
    0.06
    Restaurant
    0.06
    itore
    0.06
     김
    0.06
    health
    0.06
     افراد
    0.06
    BLEM
    0.06
    Qu
    0.06
    Act Density 0.000%

    No Known Activations