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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    noteq
    -0.07
    ěstí
    -0.07
    幹線
    -0.07
    Hashtable
    -0.07
    ostí
    -0.06
     땅
    -0.06
     chụp
    -0.06
    Shape
    -0.06
    Mic
    -0.06
    .dependencies
    -0.06
    POSITIVE LOGITS
    :!
    0.07
    rolls
    0.06
    567
    0.06
     overlooking
    0.06
     テ
    0.06
     incel
    0.06
    _full
    0.05
    ›
    0.05
     Nora
    0.05
    adic
    0.05
    Act Density 0.084%

    No Known Activations