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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    قلت
    -0.08
    placing
    -0.08
     التقرير
    -0.08
     качество
    -0.08
     رپورٹ
    -0.08
     Branding
    -0.08
     clínica
    -0.08
     Qualitäts
    -0.08
     Clínica
    -0.08
     kwaliteit
    -0.08
    POSITIVE LOGITS
     adjacency
    0.08
     adjacent
    0.08
     tids
    0.08
     octave
    0.08
    ilege
    0.08
     unions
    0.07
     zeit
    0.07
    ，例如
    0.07
    (Adapter
    0.07
     +/-
    0.07
    Act Density 0.024%

    No Known Activations