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

    Neuronpedia

    INDEX
    Explanations

    Matching, benefit, and covering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.70
     financières
    -0.70
     hjälp
    -0.69
     complètes
    -0.65
     of
    -0.65
     démocr
    -0.64
     âgées
    -0.61
    guien
    -0.61
     réguli
    -0.60
     preuve
    -0.60
    POSITIVE LOGITS
     the
    1.81
     a
    1.24
     their
    1.19
     its
    1.13
     an
    1.10
     them
    1.08
     our
    1.04
     those
    0.96
     your
    0.96
     his
    0.96
    Act Density 0.091%

    No Known Activations