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

    Neuronpedia

    INDEX
    Explanations

    compare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lowercase
    -0.07
     uu
    -0.07
    -box
    -0.06
     stu
    -0.06
    変
    -0.06
     uživatel
    -0.06
     busca
    -0.06
    ========↵
    -0.06
    ibu
    -0.06
     fragmented
    -0.06
    POSITIVE LOGITS
    _PRODUCTS
    0.07
     disagreement
    0.06
     sword
    0.06
     Mey
    0.06
    stairs
    0.06
    IPA
    0.06
     compos
    0.06
    ond
    0.06
    (commit
    0.06
    _VM
    0.06
    Act Density 0.012%

    No Known Activations