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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rex
    -0.07
    cell
    -0.07
    Ray
    -0.06
     Israel
    -0.06
    phil
    -0.06
     gboolean
    -0.06
    .Repository
    -0.06
    Billy
    -0.06
    Big
    -0.06
     American
    -0.06
    POSITIVE LOGITS
    omes
    0.07
    outines
    0.06
    َع
    0.06
    kehr
    0.06
     cl
    0.06
    لم
    0.06
    ughter
    0.06
     기반
    0.06
    Parent
    0.06
    COMM
    0.06
    Act Density 0.035%

    No Known Activations