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

    Neuronpedia

    INDEX
    Explanations

    change, share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.76
     متعلقه
    -0.71
     brancas
    -0.62
     femininas
    -0.60
     betrekking
    -0.57
     igång
    -0.57
    IsContent
    -0.56
     pronti
    -0.56
     gång
    -0.54
     paio
    -0.54
    POSITIVE LOGITS
     the
    1.24
     any
    0.81
     their
    0.81
     some
    0.78
     an
    0.77
     a
    0.75
     its
    0.74
     all
    0.73
     his
    0.73
     this
    0.71
    Act Density 0.057%

    No Known Activations