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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Weekly
    -0.07
     ignited
    -0.06
     Δ
    -0.06
     egy
    -0.06
     nasal
    -0.06
     SW
    -0.06
     dak
    -0.06
     wast
    -0.06
     EXIT
    -0.06
     SPL
    -0.06
    POSITIVE LOGITS
    زار
    0.07
    乌
    0.06
    ategy
    0.06
     آنلاین
    0.06
     good
    0.06
    ziel
    0.06
    意
    0.06
     предназнач
    0.06
    TableView
    0.06
    试
    0.06
    Act Density 0.000%

    No Known Activations