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

    Neuronpedia

    INDEX
    Explanations

    questions and reflections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compound
    -0.08
     khăn
    -0.07
    outs
    -0.07
     airy
    -0.07
    КО
    -0.07
     monuments
    -0.06
     recalled
    -0.06
     PEN
    -0.06
    dummy
    -0.06
     Spiritual
    -0.06
    POSITIVE LOGITS
    発表
    0.07
    ewire
    0.07
     Exped
    0.06
    戶
    0.06
    ([...
    0.06
    ительное
    0.06
     MongoDB
    0.06
     đổ
    0.06
     {[
    0.06
    exampleModalLabel
    0.06
    Act Density 0.035%

    No Known Activations